In [1]:
import numpy as np
import keras as k
import matplotlib.pylab as plt
import matplotlib as mpl
import keras.backend as kbck
from keras.models import  Model
from keras.layers import Dense, Dropout, Activation, Flatten, Input
from keras.layers.merge import add
import tensorflow as tf
import timeit
import random
import linear_env
%matplotlib inline


Using TensorFlow backend.

In [42]:
## Based on https://github.com/yanpanlau/DDPG-Keras-Torcs
HIDDEN1_UNITS = 150
HIDDEN2_UNITS = 300
class Actor(object):
    def __init__(self, sess, state_size, action_size, BATCH_SIZE, TAU, LEARNING_RATE):
        self.sess = sess
        self.BATCH_SIZE = BATCH_SIZE
        self.TAU = TAU
        self.LEARNING_RATE = LEARNING_RATE

        kbck.set_session(sess)

        #Now create the model
        self.munet , self.weights, self.state = self.actor_network(state_size, action_size)   
        self.target_munet, self.target_weights, self.target_state = self.actor_network(state_size, action_size) 
        self.action_gradient = tf.placeholder(tf.float32,[None, action_size])
        self.params_grad = tf.gradients(self.munet.output, self.weights, -self.action_gradient)
        grads = zip(self.params_grad, self.weights)
        self.optimize = tf.train.AdamOptimizer(LEARNING_RATE).apply_gradients(grads)
        tf.global_variables_initializer()
        
    def train(self, states, action_grads):
        self.sess.run(self.optimize, feed_dict={
            self.state: states,
            self.action_gradient: action_grads
        })

    def target_train(self):
        actor_weights = self.munet.get_weights()
        actor_target_weights = self.target_munet.get_weights()
        for i in range(len(actor_weights)):
            actor_target_weights[i] = self.TAU * actor_weights[i] + (1 - self.TAU)* actor_target_weights[i]
        self.target_munet.set_weights(actor_target_weights)

    def actor_network(self, state_size,action_dim):
        print("Building actor network...")
        S = Input(shape=[state_size],name="state_actor_input")   
        h0 = Dense(HIDDEN1_UNITS, activation='relu')(S)
        h1 = Dense(HIDDEN2_UNITS, activation='relu')(h0)
        mu = Dense(8,activation='sigmoid',kernel_initializer='he_normal',bias_initializer='zeros')(h1)   
        munet = Model(inputs=S,outputs=mu)
        return munet, munet.trainable_weights, S

In [43]:
class Critic(object):
    def __init__(self, sess, state_size, action_size, BATCH_SIZE, TAU, LEARNING_RATE):
        self.sess = sess
        self.BATCH_SIZE = BATCH_SIZE
        self.TAU = TAU
        self.LEARNING_RATE = LEARNING_RATE
        self.action_size = action_size
        
        kbck.set_session(sess)

        #Now create the model
        self.qnet, self.action, self.state = self.critic_network(state_size, action_size)  
        self.target_qnet, self.target_action, self.target_state = self.critic_network(state_size, action_size)  
        self.action_grads = tf.gradients(self.qnet.output, self.action)  #GRADIENTS for policy update
        tf.global_variables_initializer()

    def gradients(self, states, actions):
        return self.sess.run(self.action_grads, feed_dict={
            self.state: states,
            self.action: actions
        })[0]

    def target_train(self):
        critic_weights = self.qnet.get_weights()
        critic_target_weights = self.target_qnet.get_weights()
        for i in range(len(critic_weights)):
            critic_target_weights[i] = self.TAU * critic_weights[i] + (1 - self.TAU)* critic_target_weights[i]
        self.target_qnet.set_weights(critic_target_weights)

    def critic_network(self, state_size, action_dim):
        print("Building critic network...")
        S = Input(shape=[state_size],name='state_critic')  
        A = Input(shape=[action_dim],name='action_critic')   
        w1 = Dense(HIDDEN1_UNITS, activation='relu')(S)
        a1 = Dense(HIDDEN2_UNITS, activation='linear')(A) 
        h1 = Dense(HIDDEN2_UNITS, activation='linear')(w1)
        h2 = add([h1,a1])    
        h3 = Dense(HIDDEN2_UNITS, activation='relu')(h2)
        Q = Dense(action_dim,activation='linear')(h3)   
        qnet = Model(inputs=[S,A],outputs=Q)
        adam = k.optimizers.Adam(lr=self.LEARNING_RATE)
        qnet.compile(loss='mse', optimizer=adam)

        return qnet, A, S

In [44]:
class ReplayBuffer(object):

    def __init__(self, buffer_size):
        self.buffer_size = buffer_size
        self.num_experiences = 0
        self.buffer = deque()

    def getBatch(self, batch_size):
        # Randomly sample batch_size examples
        if self.num_experiences < batch_size:
            return random.sample(self.buffer, self.num_experiences)
        else:
            return random.sample(self.buffer, batch_size)

    def size(self):
        return self.buffer_size

    def add(self, state, action, reward, new_state, done):
        experience = (state, action, reward, new_state, done)
        if self.num_experiences < self.buffer_size:
            self.buffer.append(experience)
            self.num_experiences += 1
        else:
            self.buffer.popleft()
            self.buffer.append(experience)

    def count(self):
        return self.num_experiences

    def erase(self):
        self.buffer = deque()
        self.num_experiences = 0

In [48]:
def ou(x, mu, theta, sigma):
    return theta * (mu - x) + sigma * np.random.randn(np.shape(x)[0])

def simulate(train=0):    #1 means Train, 0 means simply Run
    BUFFER_SIZE = 100000
    BATCH_SIZE = 30
    GAMMA = 0.99
    TAU = 0.001     #Target Network HyperParameters
    LRA = 0.0001    #Learning rate for Actor
    LRC = 0.001     #Lerning rate for Critic

    action_dim = 8  #Steering/Acceleration/Brake
    state_dim = 10  #of sensors input

    np.random.seed(1337)

    vision = False

    EXPLORE = 10000.
    episode_count = 2000
    max_steps = 100000
    reward = 0
    done = False
    step = 0
    epsilon = 1
    indicator = 0
    
    # Constants for the linear environment
    Hs = 3600
    A1 = 0.018;
    A2 = 0.03;
    mu = 500;
    sigma = 250;
    dt = 1
    x = np.arange(Hs)
    d = np.zeros((2,Hs))
    d[0,:] = A1*np.exp((-1*(x-mu)**2)/(2*sigma**2))
    d[1,:] = A2*np.exp((-1*(x-mu)**2)/(2*sigma**2))
    vref = np.zeros((state_dim,))

    #Tensorflow GPU optimization
    config = tf.ConfigProto()
    config.gpu_options.allow_growth = True
    sess = tf.Session(config=config)
    kbck.set_session(sess)
    
    # Actor, critic and replay buffer creation
    actor = Actor(sess, state_dim, action_dim, BATCH_SIZE, TAU, LRA)
    critic = Critic(sess, state_dim, action_dim, BATCH_SIZE, TAU, LRC)
    buff = ReplayBuffer(BUFFER_SIZE)

    # Get the linear environment
    env  = linear_env.env(dt,d,vref)

    for i in range(episode_count):

        print("Episode : " + str(i) + " Replay Buffer " + str(buff.count()))
        s_t = env.reset()
        total_reward = 0.
        
        for j in range(max_steps):
            
            ## Noise addition for exploration
            ## Ornstein-Uhlenbeck process
            loss = 0 
            epsilon -= 1.0 / EXPLORE
            a_t = np.zeros([1,action_dim])
            noise_t = np.zeros([1,action_dim])
            
            a_t_original = actor.munet.predict(s_t.reshape(1, s_t.shape[0]))
            
            noise_t[0] = train * max(epsilon, 0) * ou(a_t_original[0],  0.5 , 1.00, 0.10)
            
            a_t[0]  = a_t_original[0] + noise_t[0]
            
            #Act over the system and get info of the next states
            s_t1 , r_t, done = env.step(a_t[0])

            
            #Add replay buffer
            buff.add(s_t, a_t[0], r_t, s_t1, done)   
            
            #Do the batch update
            batch = buff.getBatch(BATCH_SIZE)
            states = np.asarray([e[0] for e in batch])
            actions = np.asarray([e[1] for e in batch])
            rewards = np.asarray([e[2] for e in batch])
            next_states = np.asarray([e[3] for e in batch])
            dones = np.asarray([e[4] for e in batch])
            
            # Get estimated q-values of the pair (next_state,mu(next_state))
            actions_next = actor.target_munet.predict(next_states)
            target_q_values = critic.target_qnet.predict([next_states, actions_next]) 
            y_t = np.zeros(np.shape(actions))
           
            for k in range(len(batch)):
                if dones[k]:
                    y_t[k] = rewards[k]
                else:
                    y_t[k] = rewards[k] + GAMMA*target_q_values[k]
       
            if (train):
                loss += critic.qnet.train_on_batch([states,actions], y_t) 
                a_for_grad = actor.munet.predict(states)
                grads = critic.gradients(states, a_for_grad)
                actor.train(states, grads)
                actor.target_train()
                critic.target_train()

            total_reward = GAMMA*total_reward + r_t
            s_t = s_t1
        
            print("Episode", i, "Step", step, "Reward", r_t, "Loss", loss)
        
            step += 1
            if done:
                break

        if i%3 == 0:
            if (train):
                print("Now we save model")
                actor.model.save_weights("actormodel.h5", overwrite=True)
                with open("actormodel.json", "w") as outfile:
                    json.dump(actor.model.to_json(), outfile)

                critic.model.save_weights("criticmodel.h5", overwrite=True)
                with open("criticmodel.json", "w") as outfile:
                    json.dump(critic.model.to_json(), outfile)

        print("TOTAL REWARD @ " + str(i) +"-th Episode  : Reward " + str(total_reward))
        print("Total Step: " + str(step))
        print("")

    env.end()
    print("Finish.")

if __name__ == "__main__":
    simulate(train=1)


Building actor network...
Building actor network...
Building critic network...
Building critic network...
Simulation time set to the perturbation time: 3600 [1 s]
Episode : 0 Replay Buffer 0
Episode 0 Step 0 Action [[ 0.53399719  0.54252915  0.49868326  0.48211839  0.54049988  0.26504196
   0.45754082  0.27336179]] Reward -30.921769603 Loss 963.494018555
Episode 0 Step 1 Action [[ 0.47298488  0.60339388  0.38887158  0.48158001  0.51838558  0.56589319
   0.55791549  0.59444623]] Reward -53.3747708569 Loss 1906.86999512
Episode 0 Step 2 Action [[ 0.58699207  0.54971065  0.6553393   0.60980877  0.26916711  0.38395697
   0.61719785  0.55015211]] Reward -70.5506739142 Loss 2919.66577148
Episode 0 Step 3 Action [[ 0.5882564   0.54514983  0.5038658   0.43369448  0.61385414  0.58145288
   0.33015713  0.52811345]] Reward -93.1321225733 Loss 4329.31347656
Episode 0 Step 4 Action [[ 0.55031773  0.57235802  0.45754597  0.57789852  0.35000095  0.57360938
   0.46485316  0.56349775]] Reward -118.05992108 Loss 6192.52929688
Episode 0 Step 5 Action [[ 0.38227854  0.50287227  0.56840389  0.53285626  0.65556564  0.52234765
   0.70091925  0.45212649]] Reward -148.976602871 Loss 8755.80566406
Episode 0 Step 6 Action [[ 0.64239896  0.52675167  0.46821748  0.67446834  0.57526352  0.53358062
   0.24144048  0.44922187]] Reward -174.799043911 Loss 11700.0849609
Episode 0 Step 7 Action [[ 0.51538863  0.46425218  0.4453071   0.75323833  0.56002888  0.39065428
   0.4967315   0.54701739]] Reward -203.069040983 Loss 15126.8583984
Episode 0 Step 8 Action [[ 0.38274821  0.50946001  0.30812371  0.50421039  0.43755883  0.56559618
   0.69424766  0.57589535]] Reward -232.606349397 Loss 19066.6464844
Episode 0 Step 9 Action [[ 0.52067063  0.68427406  0.44220652  0.47633638  0.64506968  0.59936509
   0.42002762  0.57176203]] Reward -265.774522916 Loss 23656.1582031
Episode 0 Step 10 Action [[ 0.44736369  0.36674445  0.35736952  0.49457322  0.58480167  0.46298025
   0.38490352  0.4907443 ]] Reward -293.520659355 Loss 28541.625
Episode 0 Step 11 Action [[ 0.59336159  0.45572655  0.4467428   0.30192125  0.56033959  0.44913394
   0.42783758  0.41046212]] Reward -321.831674261 Loss 33708.3671875
Episode 0 Step 12 Action [[ 0.49282756  0.42395375  0.36856588  0.38248173  0.5406018   0.5349877
   0.54582895  0.66292605]] Reward -350.590603246 Loss 39103.4453125
Episode 0 Step 13 Action [[ 0.44842554  0.54504458  0.58104168  0.46876891  0.63312003  0.54622018
   0.5814926   0.52397847]] Reward -381.489203042 Loss 44752.0039062
Episode 0 Step 14 Action [[ 0.54890763  0.45451609  0.69810407  0.63797897  0.42233419  0.66444796
   0.52910113  0.56949013]] Reward -410.437357475 Loss 50422.7890625
Episode 0 Step 15 Action [[ 0.57406667  0.58601953  0.4242704   0.67905635  0.44153034  0.5024505
   0.38904471  0.48184068]] Reward -437.121510961 Loss 55881.9765625
Episode 0 Step 16 Action [[ 0.68730454  0.50959324  0.38460934  0.4087448   0.51983539  0.58030643
   0.69399371  0.47151413]] Reward -467.706194334 Loss 61193.28125
Episode 0 Step 17 Action [[ 0.62138313  0.49662732  0.34546824  0.65012635  0.48898051  0.5208299
   0.65807345  0.45170265]] Reward -495.725441886 Loss 66051.015625
Episode 0 Step 18 Action [[ 0.48024566  0.54016614  0.46424677  0.50858683  0.6480023   0.58011671
   0.63064048  0.66473463]] Reward -529.168638459 Loss 70530.7578125
Episode 0 Step 19 Action [[ 0.51419809  0.51496222  0.60271644  0.52974754  0.43951582  0.50288362
   0.55376452  0.41137349]] Reward -557.036079374 Loss 74120.9453125
Episode 0 Step 20 Action [[ 0.43716725  0.49305526  0.58744078  0.39217999  0.58571585  0.64799317
   0.40137851  0.64186511]] Reward -590.113514506 Loss 76839.09375
Episode 0 Step 21 Action [[ 0.65174957  0.45197896  0.45211694  0.45740447  0.4602773   0.4789488
   0.33239968  0.56812384]] Reward -616.3582077 Loss 78108.546875
Episode 0 Step 22 Action [[ 0.61933802  0.42632857  0.48097498  0.49637414  0.37961226  0.60514096
   0.36281852  0.34000163]] Reward -643.613884298 Loss 77792.1015625
Episode 0 Step 23 Action [[ 0.37783626  0.41768396  0.55077043  0.75115827  0.47697159  0.60083317
   0.66546664  0.42318829]] Reward -673.400515941 Loss 75761.9296875
Episode 0 Step 24 Action [[ 0.58859819  0.49800035  0.49558038  0.39321959  0.63570505  0.63256915
   0.53530698  0.59520301]] Reward -707.043010743 Loss 71950.296875
Episode 0 Step 25 Action [[ 0.57095749  0.3946306   0.50911416  0.6370984   0.56904317  0.52530811
   0.33833661  0.47004621]] Reward -736.526584614 Loss 66056.1875
Episode 0 Step 26 Action [[ 0.67810997  0.65433468  0.53011067  0.34274247  0.6722254   0.3859546
   0.35519261  0.5977773 ]] Reward -767.27265505 Loss 58128.8203125
Episode 0 Step 27 Action [[ 0.48316807  0.45312537  0.3929915   0.43527513  0.4780795   0.6717097
   0.58193513  0.52598478]] Reward -797.403324172 Loss 48339.25
Episode 0 Step 28 Action [[ 0.72092464  0.6223283   0.47485442  0.48956588  0.43899338  0.4440839
   0.28222214  0.56990405]] Reward -823.234548868 Loss 37151.7890625
Episode 0 Step 29 Action [[ 0.29347747  0.65516035  0.4419415   0.48239927  0.6126692   0.60636558
   0.44520079  0.56699939]] Reward -855.544870908 Loss 25632.3496094
Episode 0 Step 30 Action [[ 0.38852185  0.54512353  0.37387228  0.41372787  0.37668405  0.60360536
   0.27023946  0.43451335]] Reward -882.34020472 Loss 15360.5058594
Episode 0 Step 31 Action [[ 0.55023566  0.59283232  0.39707226  0.55850464  0.51160915  0.49088995
   0.37594125  0.39119725]] Reward -909.835612695 Loss 8136.14599609
Episode 0 Step 32 Action [[ 0.50979614  0.59532808  0.50158764  0.37538689  0.60068088  0.44639914
   0.46719484  0.45839444]] Reward -939.07809139 Loss 5850.97851562
Episode 0 Step 33 Action [[ 0.30918351  0.56138822  0.43787606  0.5043333   0.42317175  0.44738184
   0.44280365  0.50811303]] Reward -964.394268059 Loss 10834.8417969
Episode 0 Step 34 Action [[ 0.53079471  0.46947221  0.42090983  0.57046388  0.4706955   0.49742711
   0.59845566  0.49500728]] Reward -991.068354575 Loss 18877.3671875
Episode 0 Step 35 Action [[ 0.51198191  0.66872431  0.33402998  0.52113342  0.50926158  0.57788822
   0.50813132  0.69894563]] Reward -1020.881435 Loss 24881.8046875
Episode 0 Step 36 Action [[ 0.50563001  0.38402933  0.47849685  0.55989319  0.35904631  0.40140342
   0.46038392  0.26463687]] Reward -1044.34438768 Loss 26487.578125
Episode 0 Step 37 Action [[ 0.50058617  0.62164625  0.60548628  0.30567948  0.4886658   0.44372323
   0.61559425  0.49854533]] Reward -1072.80419634 Loss 20524.4785156
Episode 0 Step 38 Action [[ 0.63756298  0.41692832  0.61661775  0.44748291  0.55142812  0.43440687
   0.32983416  0.50325073]] Reward -1099.76529931 Loss 15494.7617188
Episode 0 Step 39 Action [[ 0.59229164  0.45396324  0.51793559  0.67212242  0.58087506  0.48608271
   0.57609776  0.52085472]] Reward -1128.38730075 Loss 6255.33984375
Episode 0 Step 40 Action [[ 0.47897919  0.57559087  0.5554048   0.45907685  0.66369778  0.52713309
   0.3985898   0.41578928]] Reward -1160.53374642 Loss 1402.97900391
Episode 0 Step 41 Action [[ 0.59167404  0.57915701  0.53673909  0.40037628  0.3658161   0.37509769
   0.5042612   0.43699443]] Reward -1184.60764312 Loss 149.289886475
Episode 0 Step 42 Action [[ 0.63041479  0.56828266  0.56392427  0.51136772  0.64993263  0.42058495
   0.39910379  0.64561292]] Reward -1213.94027687 Loss 1381.94091797
Episode 0 Step 43 Action [[ 0.64552311  0.56074678  0.51650795  0.44357895  0.47644448  0.51235507
   0.66853902  0.47823697]] Reward -1241.87856122 Loss 5677.87109375
Episode 0 Step 44 Action [[ 0.66128203  0.50980047  0.73921293  0.49757099  0.53839525  0.51469801
   0.52607511  0.26370218]] Reward -1271.12379323 Loss 10689.2626953
Episode 0 Step 45 Action [[ 0.50718659  0.54619226  0.36672555  0.4243189   0.80452255  0.59979196
   0.57945815  0.58648811]] Reward -1305.66945096 Loss 9918.76757812
Episode 0 Step 46 Action [[ 0.64725938  0.45445897  0.51472169  0.44291791  0.45829601  0.62593843
   0.41274675  0.50257166]] Reward -1334.42871822 Loss 10789.4394531
Episode 0 Step 47 Action [[ 0.3981951   0.34660581  0.4011226   0.45393094  0.39226135  0.46033092
   0.54355697  0.53976529]] Reward -1358.72742859 Loss 7968.00292969
Episode 0 Step 48 Action [[ 0.55678236  0.52872542  0.59385666  0.41348732  0.67996661  0.63629999
   0.4617459   0.44404464]] Reward -1391.93482836 Loss 6241.39648438
Episode 0 Step 49 Action [[ 0.38106652  0.37835086  0.74227223  0.60033123  0.44529349  0.43447486
   0.52063871  0.49030585]] Reward -1417.60034685 Loss 3711.50341797
Episode 0 Step 50 Action [[ 0.43587824  0.50705367  0.60553803  0.63844905  0.3642718   0.45203787
   0.58035913  0.47042349]] Reward -1442.7783956 Loss 2375.52001953
Episode 0 Step 51 Action [[ 0.50405219  0.45019937  0.5096968   0.45946468  0.39999541  0.2204882
   0.30719176  0.39222751]] Reward -1464.69713458 Loss 2767.75878906
Episode 0 Step 52 Action [[ 0.44432672  0.69199388  0.55620417  0.51824097  0.57994411  0.38719569
   0.40830543  0.46209221]] Reward -1493.48893485 Loss 4155.27832031
Episode 0 Step 53 Action [[ 0.46181799  0.31536992  0.41976907  0.43252655  0.47263762  0.40746399
   0.57929938  0.43905757]] Reward -1518.89413796 Loss 5265.51269531
Episode 0 Step 54 Action [[ 0.53478238  0.53595869  0.43025018  0.39317491  0.54444511  0.58985919
   0.34531992  0.43254132]] Reward -1549.05987415 Loss 4906.05371094
Episode 0 Step 55 Action [[ 0.4413557   0.51669062  0.63618539  0.60054519  0.35018892  0.53846466
   0.46771572  0.35473413]] Reward -1575.28869414 Loss 3259.79150391
Episode 0 Step 56 Action [[ 0.46195245  0.48429207  0.58727719  0.52737032  0.49751043  0.4394777
   0.67442459  0.54357258]] Reward -1602.7375345 Loss 1082.29321289
Episode 0 Step 57 Action [[ 0.67265154  0.55101191  0.59669681  0.58471275  0.58403329  0.50360884
   0.5381538   0.55236599]] Reward -1632.89668648 Loss 143.67388916
Episode 0 Step 58 Action [[ 0.41596579  0.66192117  0.42660402  0.37512515  0.42636306  0.42355558
   0.38243616  0.49740008]] Reward -1659.32087651 Loss 435.012207031
Episode 0 Step 59 Action [[ 0.51781501  0.53739211  0.66978189  0.51978314  0.66018141  0.45689504
   0.50028526  0.40804645]] Reward -1689.88474379 Loss 1891.98681641
Episode 0 Step 60 Action [[ 0.27331512  0.42149829  0.41807979  0.51716759  0.44918196  0.45526063
   0.53822906  0.32497388]] Reward -1715.82871004 Loss 2405.98022461
Episode 0 Step 61 Action [[ 0.35625594  0.48672596  0.39190112  0.5483428   0.58763407  0.42903548
   0.4121114   0.4596382 ]] Reward -1743.96676006 Loss 2659.71166992
Episode 0 Step 62 Action [[ 0.53404889  0.54321519  0.32430561  0.63151181  0.66796817  0.57543544
   0.41727469  0.45419321]] Reward -1776.13204085 Loss 2259.86254883
Episode 0 Step 63 Action [[ 0.38747534  0.63669765  0.48553538  0.61060929  0.61476421  0.42849481
   0.54716846  0.43362108]] Reward -1806.43815789 Loss 1364.53271484
Episode 0 Step 64 Action [[ 0.47499497  0.40286982  0.54203364  0.28263093  0.53009894  0.51452109
   0.47849201  0.58862727]] Reward -1836.26768421 Loss 753.28692627
Episode 0 Step 65 Action [[ 0.41050899  0.40809442  0.53326887  0.52611527  0.73323693  0.38638279
   0.60153494  0.48888519]] Reward -1866.09148266 Loss 733.204345703
Episode 0 Step 66 Action [[ 0.63793495  0.53310712  0.49440615  0.6191554   0.56553285  0.53784533
   0.28341384  0.53641116]] Reward -1895.93848843 Loss 1329.41223145
Episode 0 Step 67 Action [[ 0.42266348  0.48437973  0.35833028  0.50025019  0.4828611   0.60613504
   0.50472775  0.42513824]] Reward -1925.77361728 Loss 1413.68334961
Episode 0 Step 68 Action [[ 0.46360059  0.51882035  0.5060868   0.70727213  0.62032188  0.37091452
   0.42596105  0.38596173]] Reward -1954.29684301 Loss 996.435302734
Episode 0 Step 69 Action [[ 0.4539488   0.55558095  0.46307426  0.62558168  0.47284931  0.69987071
   0.45791758  0.38899039]] Reward -1986.81208515 Loss 400.016448975
Episode 0 Step 70 Action [[ 0.49428374  0.49899028  0.3978872   0.59152236  0.43817518  0.58199485
   0.45239872  0.58273611]] Reward -2016.59535748 Loss 102.647171021
Episode 0 Step 71 Action [[ 0.59220388  0.43470115  0.55718799  0.56329638  0.40958018  0.36626265
   0.6610489   0.46181763]] Reward -2042.51400712 Loss 295.727539062
Episode 0 Step 72 Action [[ 0.52116646  0.39957944  0.43751817  0.48954376  0.54428395  0.55824012
   0.56799272  0.48355657]] Reward -2073.35584634 Loss 638.186157227
Episode 0 Step 73 Action [[ 0.42509089  0.62326695  0.45164063  0.56194989  0.54870678  0.47316041
   0.2222436   0.4236678 ]] Reward -2103.08662821 Loss 1150.45056152
Episode 0 Step 74 Action [[ 0.58152008  0.45508596  0.71717529  0.63145889  0.56171167  0.49075939
   0.57098343  0.53429335]] Reward -2133.73126454 Loss 823.015625
Episode 0 Step 75 Action [[ 0.40893756  0.45185031  0.48723133  0.46402413  0.52801021  0.4423854
   0.4382074   0.58241029]] Reward -2162.53489982 Loss 424.598419189
Episode 0 Step 76 Action [[ 0.50063658  0.21992748  0.50577697  0.61791165  0.29430506  0.3872904
   0.3830273   0.75496101]] Reward -2185.25193949 Loss 265.774963379
Episode 0 Step 77 Action [[ 0.4328561   0.44628223  0.49899158  0.35328176  0.47307324  0.56389254
   0.33615195  0.3354491 ]] Reward -2214.98560822 Loss 387.801818848
Episode 0 Step 78 Action [[ 0.47424487  0.55034624  0.56511817  0.55641866  0.52698665  0.59139464
   0.39308608  0.59585247]] Reward -2245.71476692 Loss 656.676025391
Episode 0 Step 79 Action [[ 0.49193313  0.48485364  0.54565333  0.4828033   0.49753223  0.64327798
   0.54309817  0.57978227]] Reward -2276.72090431 Loss 417.098297119
Episode 0 Step 80 Action [[ 0.54192233  0.62383003  0.5308333   0.54463381  0.48420596  0.45741999
   0.35419484  0.58621053]] Reward -2304.47728161 Loss 112.048522949
Episode 0 Step 81 Action [[ 0.64271868  0.50567627  0.3002314   0.50935498  0.52172938  0.40700231
   0.36215218  0.49246452]] Reward -2331.10457439 Loss 110.097175598
Episode 0 Step 82 Action [[ 0.46440751  0.64535806  0.39280291  0.46529287  0.42348898  0.35858864
   0.45458868  0.42160957]] Reward -2356.04162677 Loss 253.743133545
Episode 0 Step 83 Action [[ 0.54106267  0.33982919  0.65616147  0.37420709  0.24500723  0.52613529
   0.37094556  0.60083821]] Reward -2380.31608764 Loss 346.383422852
Episode 0 Step 84 Action [[ 0.4410533   0.51179097  0.5124409   0.38395932  0.49447912  0.33675668
   0.42288154  0.53161556]] Reward -2405.11167858 Loss 276.610290527
Episode 0 Step 85 Action [[ 0.25527318  0.61609499  0.45532998  0.52156062  0.63265375  0.44727792
   0.71529175  0.47634249]] Reward -2434.00483699 Loss 140.758270264
Episode 0 Step 86 Action [[ 0.47279349  0.56300336  0.40087977  0.58842889  0.4929304   0.53260448
   0.46036036  0.57987273]] Reward -2461.76269199 Loss 172.54473877
Episode 0 Step 87 Action [[ 0.68352426  0.60520773  0.56970481  0.42530384  0.54180994  0.41775557
   0.44378423  0.4889232 ]] Reward -2489.74186454 Loss 203.45880127
Episode 0 Step 88 Action [[ 0.52884153  0.4931895   0.41991144  0.593499    0.42913999  0.3484082
   0.39079575  0.3915711 ]] Reward -2513.46670014 Loss 159.543395996
Episode 0 Step 89 Action [[ 0.52826931  0.49925329  0.53761354  0.54404301  0.52947242  0.64373262
   0.25598349  0.34757479]] Reward -2544.915713 Loss 82.5655822754
Episode 0 Step 90 Action [[ 0.42118787  0.3044422   0.48331544  0.47812171  0.53290165  0.45456621
   0.49740012  0.33439436]] Reward -2572.6486514 Loss 78.5963897705
Episode 0 Step 91 Action [[ 0.49199555  0.68402779  0.64146833  0.45777152  0.46006405  0.47852976
   0.73001834  0.49483718]] Reward -2601.10030134 Loss 112.984138489
Episode 0 Step 92 Action [[ 0.38059877  0.32456628  0.51712792  0.59205179  0.47408886  0.52580359
   0.52795321  0.51177918]] Reward -2628.55889508 Loss 134.74331665
Episode 0 Step 93 Action [[ 0.5187699   0.39805502  0.5373232   0.59281072  0.31513685  0.43976849
   0.40195046  0.23665891]] Reward -2652.67577213 Loss 121.405143738
Episode 0 Step 94 Action [[ 0.61269405  0.59723358  0.60926398  0.2957643   0.65801437  0.77800216
   0.43523888  0.48025713]] Reward -2689.70986549 Loss 102.543052673
Episode 0 Step 95 Action [[ 0.50528882  0.37995632  0.37139299  0.48152656  0.3875964   0.64427138
   0.62646181  0.53691194]] Reward -2717.21750002 Loss 76.7735366821
Episode 0 Step 96 Action [[ 0.54547685  0.50763107  0.5156066   0.53046571  0.38958401  0.54513735
   0.57242761  0.47424326]] Reward -2743.92203642 Loss 108.672401428
Episode 0 Step 97 Action [[ 0.62274366  0.46343202  0.54278061  0.43839002  0.56376618  0.61226048
   0.50263416  0.4669684 ]] Reward -2774.9270604 Loss 76.5814208984
Episode 0 Step 98 Action [[ 0.3528123   0.31887687  0.55145105  0.61400454  0.41593119  0.44084467
   0.38205146  0.44987322]] Reward -2799.87613401 Loss 52.0988235474
Episode 0 Step 99 Action [[ 0.64972224  0.53174537  0.5689404   0.39511454  0.69028431  0.34559483
   0.46703283  0.50298826]] Reward -2829.2353707 Loss 51.6283531189
Episode 0 Step 100 Action [[ 0.32256747  0.38040699  0.40191266  0.33469581  0.44024147  0.49904443
   0.38566032  0.58079703]] Reward -2855.42515131 Loss 69.4184036255
Episode 0 Step 101 Action [[ 0.42236477  0.48327902  0.45039375  0.53028454  0.51963352  0.37060631
   0.64548345  0.63622581]] Reward -2880.57425341 Loss 59.0326080322
Episode 0 Step 102 Action [[ 0.49694467  0.67707776  0.52635924  0.45547251  0.497888    0.57678103
   0.47273689  0.532653  ]] Reward -2909.99978069 Loss 54.9566078186
Episode 0 Step 103 Action [[ 0.27735656  0.58532546  0.53351296  0.40706225  0.42486374  0.52179467
   0.43736389  0.41137181]] Reward -2936.97836547 Loss 57.8403205872
Episode 0 Step 104 Action [[ 0.38548382  0.65385631  0.44412385  0.57114554  0.61221598  0.55681369
   0.68563522  0.63794833]] Reward -2967.46724952 Loss 30.9466381073
Episode 0 Step 105 Action [[ 0.67635204  0.40159217  0.52726046  0.52355608  0.46587034  0.2681003
   0.43455293  0.55195918]] Reward -2990.43883272 Loss 25.7483482361
Episode 0 Step 106 Action [[ 0.55612907  0.39037575  0.47939102  0.6248555   0.49004976  0.34167486
   0.54833287  0.56707131]] Reward -3015.32555436 Loss 56.3834686279
Episode 0 Step 107 Action [[ 0.41041788  0.51619387  0.53047568  0.27397822  0.53638522  0.58001983
   0.47881968  0.25172617]] Reward -3046.16494114 Loss 44.8634567261
Episode 0 Step 108 Action [[ 0.51368711  0.62043072  0.27385932  0.34347693  0.55913352  0.52600162
   0.29219851  0.58184517]] Reward -3074.73439885 Loss 43.8936462402
Episode 0 Step 109 Action [[ 0.4199956   0.64189357  0.56443847  0.60282812  0.34104502  0.53898505
   0.39684567  0.33035048]] Reward -3100.23763822 Loss 68.772315979
Episode 0 Step 110 Action [[ 0.52703359  0.51313295  0.53221987  0.39129319  0.4498006   0.43156465
   0.38768707  0.52807601]] Reward -3126.07371282 Loss 39.15599823
Episode 0 Step 111 Action [[ 0.50083156  0.46079127  0.52267445  0.47299896  0.61117652  0.43276551
   0.55704057  0.48584627]] Reward -3154.14545544 Loss 58.3352966309
Episode 0 Step 112 Action [[ 0.45841021  0.48775092  0.45407199  0.40112492  0.48982834  0.54983358
   0.44167639  0.55680031]] Reward -3182.10388486 Loss 27.6537189484
Episode 0 Step 113 Action [[ 0.54841643  0.47473628  0.24314191  0.32007765  0.4978728   0.3641677
   0.50851265  0.60574575]] Reward -3206.09859864 Loss 43.1857795715
Episode 0 Step 114 Action [[ 0.43392268  0.29884485  0.4961787   0.54659223  0.36534525  0.51403137
   0.54741538  0.54536281]] Reward -3230.04597556 Loss 52.472038269
Episode 0 Step 115 Action [[ 0.49289405  0.44201471  0.5175735   0.62085454  0.55008379  0.38879766
   0.64390998  0.31271573]] Reward -3256.15622451 Loss 37.6135749817
Episode 0 Step 116 Action [[ 0.37869247  0.40543883  0.56306916  0.4436012   0.66285512  0.40055202
   0.44418236  0.50069124]] Reward -3285.31627001 Loss 27.186580658
Episode 0 Step 117 Action [[ 0.37815202  0.69889586  0.5008374   0.47639434  0.51102798  0.50924228
   0.57633996  0.50057349]] Reward -3314.1952411 Loss 48.3798141479
Episode 0 Step 118 Action [[ 0.56920563  0.50672233  0.38186608  0.47205456  0.45586659  0.54008585
   0.37914335  0.5893568 ]] Reward -3341.52049136 Loss 22.5862293243
Episode 0 Step 119 Action [[ 0.48714737  0.34260358  0.30972429  0.61618481  0.40508051  0.39988622
   0.45687247  0.54708519]] Reward -3364.99760145 Loss 40.117313385
Episode 0 Step 120 Action [[ 0.51671112  0.52474932  0.5105647   0.4986001   0.61455218  0.4604144
   0.68732543  0.48543528]] Reward -3394.95074449 Loss 36.292842865
Episode 0 Step 121 Action [[ 0.50682817  0.62688962  0.49822186  0.41194918  0.43416504  0.5993385
   0.46407584  0.46557644]] Reward -3424.24456623 Loss 29.0242195129
Episode 0 Step 122 Action [[ 0.54625595  0.54222151  0.52191932  0.43213499  0.58684048  0.5454857
   0.62604422  0.52461853]] Reward -3454.59740376 Loss 43.3138046265
Episode 0 Step 123 Action [[ 0.43317964  0.47738315  0.71174705  0.42093466  0.44387425  0.48251645
   0.47967067  0.49104015]] Reward -3481.54328634 Loss 29.6258945465
Episode 0 Step 124 Action [[ 0.6387775   0.31776352  0.54229115  0.58740219  0.39841972  0.43359052
   0.50478363  0.59047529]] Reward -3505.60714303 Loss 37.0078010559
Episode 0 Step 125 Action [[ 0.51979317  0.65045661  0.69972769  0.52566299  0.51565101  0.55936092
   0.59957212  0.51820398]] Reward -3536.07813406 Loss 43.667804718
Episode 0 Step 126 Action [[ 0.57472331  0.60864974  0.43468966  0.56490207  0.47389427  0.58158842
   0.3811872   0.60421615]] Reward -3565.26745773 Loss 33.3091278076
Episode 0 Step 127 Action [[ 0.41777453  0.46666435  0.51355594  0.56997206  0.51616542  0.39976324
   0.4991551   0.55869924]] Reward -3592.34677576 Loss 37.1230545044
Episode 0 Step 128 Action [[ 0.4425955   0.39031172  0.50280219  0.50146984  0.51856951  0.57840362
   0.58604736  0.34615919]] Reward -3622.42581124 Loss 44.8763275146
Episode 0 Step 129 Action [[ 0.3680538   0.43082886  0.27004645  0.44256811  0.3536558   0.31051408
   0.54172468  0.36681119]] Reward -3644.43319867 Loss 37.1217079163
Episode 0 Step 130 Action [[ 0.47667586  0.5594885   0.5279705   0.52742696  0.48117633  0.52030087
   0.47379113  0.38979983]] Reward -3672.94599498 Loss 38.0620689392
Episode 0 Step 131 Action [[ 0.60993335  0.52575837  0.36511113  0.43194833  0.41364226  0.34024967
   0.34208538  0.43604588]] Reward -3696.70030952 Loss 30.2851142883
Episode 0 Step 132 Action [[ 0.65667376  0.44420003  0.56108162  0.32337931  0.50701149  0.3559528
   0.38876543  0.42379722]] Reward -3722.33210158 Loss 28.3123626709
Episode 0 Step 133 Action [[ 0.43112911  0.38333962  0.47772317  0.66708143  0.55501503  0.54178819
   0.60425916  0.49656175]] Reward -3750.77591478 Loss 33.324672699
Episode 0 Step 134 Action [[ 0.42343731  0.44208701  0.42670796  0.57571725  0.45531337  0.40246152
   0.37620278  0.43789076]] Reward -3776.20603396 Loss 42.80884552
Episode 0 Step 135 Action [[ 0.43663099  0.24978475  0.51944358  0.42451372  0.54844002  0.55819388
   0.30340782  0.50088875]] Reward -3805.96644136 Loss 24.3401050568
Episode 0 Step 136 Action [[ 0.60187468  0.5731094   0.45022827  0.38821687  0.33564354  0.33286304
   0.41024378  0.64436128]] Reward -3828.54421835 Loss 47.4749946594
Episode 0 Step 137 Action [[ 0.51047588  0.34464322  0.51969674  0.53282679  0.4423606   0.45174414
   0.47210415  0.55380298]] Reward -3853.91475636 Loss 37.3896446228
Episode 0 Step 138 Action [[ 0.33654013  0.32961969  0.42015345  0.42224263  0.46807673  0.51871972
   0.57120425  0.63994409]] Reward -3880.92867573 Loss 15.8263607025
Episode 0 Step 139 Action [[ 0.49344344  0.59585869  0.39021472  0.51772648  0.73161675  0.46731334
   0.55870985  0.41089314]] Reward -3911.85850217 Loss 42.9213447571
Episode 0 Step 140 Action [[ 0.61347348  0.44532779  0.55823002  0.30145258  0.45748566  0.49033332
   0.41179939  0.54454786]] Reward -3938.81819578 Loss 27.8038311005
Episode 0 Step 141 Action [[ 0.45306902  0.50500986  0.21820483  0.46003969  0.56138056  0.54364739
   0.49090903  0.46963713]] Reward -3966.76788103 Loss 25.9609985352
Episode 0 Step 142 Action [[ 0.58928503  0.58323929  0.54394693  0.41648205  0.61762002  0.49744902
   0.63516364  0.37372952]] Reward -3996.25020219 Loss 20.4921588898
Episode 0 Step 143 Action [[ 0.60803847  0.4798444   0.58739779  0.36122625  0.70657555  0.43610081
   0.62187559  0.31815397]] Reward -4025.86081133 Loss 36.5474967957
Episode 0 Step 144 Action [[ 0.55821728  0.46489877  0.57124295  0.58560505  0.55096557  0.44330041
   0.47696676  0.57647195]] Reward -4052.55097974 Loss 38.3844337463
Episode 0 Step 145 Action [[ 0.55342719  0.62890016  0.49748818  0.4748138   0.45041098  0.52548658
   0.59067399  0.36527405]] Reward -4080.02581444 Loss 32.9598388672
Episode 0 Step 146 Action [[ 0.38864735  0.51183889  0.37890958  0.3693681   0.55245302  0.63663311
   0.2676964   0.37096665]] Reward -4110.47928604 Loss 21.7957344055
Episode 0 Step 147 Action [[ 0.42281495  0.52593534  0.4091932   0.5185827   0.4731972   0.51570824
   0.48182262  0.42069968]] Reward -4137.24865174 Loss 26.9959220886
Episode 0 Step 148 Action [[ 0.46080781  0.30018045  0.52604136  0.48353616  0.45424617  0.34256956
   0.49928526  0.4480955 ]] Reward -4160.78783146 Loss 24.2152366638
Episode 0 Step 149 Action [[ 0.36186966  0.54712878  0.67040954  0.58642466  0.5214024   0.41237007
   0.37226231  0.47040252]] Reward -4187.98808682 Loss 40.7183837891
Episode 0 Step 150 Action [[ 0.47095135  0.41369904  0.40376974  0.61519189  0.58675037  0.44836789
   0.50186     0.48526539]] Reward -4216.21059025 Loss 43.0346870422
Episode 0 Step 151 Action [[ 0.50584493  0.40917374  0.40315774  0.61803428  0.59630458  0.62569769
   0.42525155  0.50449993]] Reward -4248.234548 Loss 27.3460445404
Episode 0 Step 152 Action [[ 0.51823845  0.50973769  0.69318168  0.42489696  0.57097747  0.54172166
   0.29625611  0.56434655]] Reward -4279.97832284 Loss 26.1292800903
Episode 0 Step 153 Action [[ 0.49301611  0.49000274  0.35510429  0.41823476  0.39339182  0.37639809
   0.41594508  0.34773231]] Reward -4304.05937969 Loss 27.9186019897
Episode 0 Step 154 Action [[ 0.45652125  0.37760296  0.63870235  0.50251669  0.60527203  0.48258835
   0.58173056  0.3834928 ]] Reward -4333.66875511 Loss 20.0581626892
Episode 0 Step 155 Action [[ 0.34375555  0.606484    0.45396014  0.49253803  0.47224825  0.64211243
   0.27310715  0.47714257]] Reward -4363.8680095 Loss 20.5192680359
Episode 0 Step 156 Action [[ 0.57687271  0.47338788  0.54698268  0.50071572  0.4713682   0.39329959
   0.61406445  0.45101448]] Reward -4389.67156616 Loss 33.6987991333
Episode 0 Step 157 Action [[ 0.45382699  0.58344542  0.50389139  0.40891868  0.60948823  0.61804642
   0.6404192   0.4784798 ]] Reward -4421.93812487 Loss 18.4881477356
Episode 0 Step 158 Action [[ 0.44537863  0.56751285  0.33789489  0.42238783  0.46622416  0.26045579
   0.5354178   0.49434461]] Reward -4444.62997194 Loss 29.4135360718
Episode 0 Step 159 Action [[ 0.46088117  0.40184213  0.46981991  0.57704849  0.33485728  0.60983546
   0.5276824   0.50446715]] Reward -4470.74122544 Loss 22.7850875854
Episode 0 Step 160 Action [[ 0.50307475  0.60734888  0.54703338  0.43919708  0.61393827  0.62395148
   0.6160205   0.60853527]] Reward -4503.33780386 Loss 26.6604251862
Episode 0 Step 161 Action [[ 0.46084529  0.54388813  0.69891021  0.49735679  0.58376027  0.32371004
   0.45076944  0.53420129]] Reward -4530.21378804 Loss 44.2079048157
Episode 0 Step 162 Action [[ 0.57732546  0.53577948  0.26824604  0.55377111  0.50509929  0.47779047
   0.35775608  0.46014448]] Reward -4557.13645227 Loss 28.3647937775
Episode 0 Step 163 Action [[ 0.62022435  0.68144058  0.5013665   0.68420708  0.5941428   0.39074447
   0.48464565  0.37084679]] Reward -4585.67500041 Loss 30.7811584473
Episode 0 Step 164 Action [[ 0.41072752  0.65158592  0.32187878  0.3967125   0.51921822  0.67550241
   0.31127607  0.37663238]] Reward -4618.03220391 Loss 35.6736564636
Episode 0 Step 165 Action [[ 0.78185295  0.37489188  0.42356231  0.58126204  0.62344782  0.49151023
   0.46705395  0.53790933]] Reward -4647.75206633 Loss 40.7756347656
Episode 0 Step 166 Action [[ 0.6235213   0.53212824  0.52606511  0.48378057  0.5138985   0.44419421
   0.56435132  0.4938958 ]] Reward -4675.92823248 Loss 79.6934051514
Episode 0 Step 167 Action [[ 0.38865331  0.52732256  0.48186906  0.49652604  0.52198356  0.65373075
   0.49798118  0.24846412]] Reward -4707.40437125 Loss 33.1796073914
Episode 0 Step 168 Action [[ 0.48904829  0.35694357  0.51235102  0.6820908   0.38486354  0.44662742
   0.35144839  0.66753566]] Reward -4732.5145103 Loss 49.9584197998
Episode 0 Step 169 Action [[ 0.65503949  0.5960726   0.53507691  0.72534583  0.42295919  0.46077467
   0.5180786   0.33415065]] Reward -4760.11042236 Loss 29.2251491547
Episode 0 Step 170 Action [[ 0.45206187  0.44628971  0.36002885  0.37725732  0.4840229   0.54340158
   0.62415444  0.44640111]] Reward -4790.06784151 Loss 48.9206008911
Episode 0 Step 171 Action [[ 0.57767666  0.58164838  0.41954784  0.45057851  0.47994042  0.4701498
   0.51464266  0.53199613]] Reward -4818.10058003 Loss 38.5654449463
Episode 0 Step 172 Action [[ 0.42616475  0.57651946  0.61789416  0.5367697   0.4455587   0.51437316
   0.48356805  0.4648433 ]] Reward -4846.43661276 Loss 79.2681427002
Episode 0 Step 173 Action [[ 0.57375635  0.34346393  0.44427151  0.40203394  0.50469161  0.6288088
   0.53632011  0.58096309]] Reward -4876.59020878 Loss 68.6552429199
Episode 0 Step 174 Action [[ 0.60006672  0.41391522  0.45260506  0.37985735  0.49183171  0.56798147
   0.41936577  0.45329726]] Reward -4905.14226414 Loss 28.4807777405
Episode 0 Step 175 Action [[ 0.4925573   0.52771011  0.53544539  0.54662148  0.30409571  0.68279255
   0.49947285  0.45103597]] Reward -4932.54857945 Loss 61.1591491699
Episode 0 Step 176 Action [[ 0.50316699  0.54978535  0.3744735   0.4316957   0.60778636  0.52488111
   0.37188245  0.43060066]] Reward -4962.42393254 Loss 36.1558685303
Episode 0 Step 177 Action [[ 0.57192999  0.49232762  0.39959021  0.27916103  0.46621414  0.51990279
   0.49943524  0.47384868]] Reward -4989.49530333 Loss 50.7234115601
Episode 0 Step 178 Action [[ 0.55603692  0.6010896   0.54680817  0.33207748  0.44634546  0.54933137
   0.62226452  0.6301276 ]] Reward -5016.58073632 Loss 112.728347778
Episode 0 Step 179 Action [[ 0.36764933  0.54914207  0.56324865  0.67500401  0.53342199  0.50782555
   0.41706358  0.34282591]] Reward -5043.84653051 Loss 96.2201690674
Episode 0 Step 180 Action [[ 0.62058064  0.21302221  0.74108064  0.33864056  0.46760395  0.46318113
   0.40273387  0.463749  ]] Reward -5070.18421601 Loss 25.1692657471
Episode 0 Step 181 Action [[ 0.3854367   0.58335094  0.45882837  0.50978742  0.53787671  0.43741118
   0.48464735  0.51843935]] Reward -5096.97158502 Loss 67.1189041138
Episode 0 Step 182 Action [[ 0.663692    0.56634413  0.42513036  0.50135901  0.61551387  0.50220284
   0.44299142  0.35344772]] Reward -5126.30987508 Loss 44.3006057739
Episode 0 Step 183 Action [[ 0.57628877  0.43854486  0.36128963  0.46838469  0.50493429  0.55976577
   0.44646529  0.53090649]] Reward -5154.49785445 Loss 49.8471755981
Episode 0 Step 184 Action [[ 0.4619964   0.4606991   0.35170819  0.66406246  0.4592062   0.40553559
   0.38876057  0.51042774]] Reward -5179.2958994 Loss 71.2593078613
Episode 0 Step 185 Action [[ 0.49680082  0.47344464  0.50635698  0.36569878  0.4600541   0.4156351
   0.70260516  0.34625813]] Reward -5205.75556504 Loss 23.6868572235
Episode 0 Step 186 Action [[ 0.44109953  0.54186768  0.34737301  0.36883893  0.3340607   0.54050437
   0.4123394   0.50254607]] Reward -5231.09066002 Loss 52.016746521
Episode 0 Step 187 Action [[ 0.42181523  0.48548833  0.48203083  0.56883356  0.5401      0.45645023
   0.49586531  0.53578011]] Reward -5258.22708428 Loss 42.399559021
Episode 0 Step 188 Action [[ 0.50238838  0.55507553  0.45142605  0.45146098  0.49695847  0.40959078
   0.58727378  0.28520486]] Reward -5284.49711428 Loss 24.8653488159
Episode 0 Step 189 Action [[ 0.60894732  0.4609968   0.54030464  0.51813616  0.47205826  0.55162488
   0.57281289  0.47667306]] Reward -5312.62792628 Loss 72.6495437622
Episode 0 Step 190 Action [[ 0.45749623  0.58787508  0.51387829  0.4160469   0.56675338  0.57439594
   0.4350791   0.50657954]] Reward -5343.2836048 Loss 133.196746826
Episode 0 Step 191 Action [[ 0.56956688  0.48396894  0.46526855  0.53496323  0.54504498  0.37603897
   0.4638849   0.57634199]] Reward -5369.35611191 Loss 53.4170188904
Episode 0 Step 192 Action [[ 0.44317267  0.44525012  0.57738524  0.45651313  0.57770724  0.63974821
   0.41284683  0.51261482]] Reward -5401.07527782 Loss 42.4081497192
Episode 0 Step 193 Action [[ 0.42527767  0.46296391  0.64819755  0.46593282  0.49127804  0.55389089
   0.42816973  0.64753379]] Reward -5429.97740714 Loss 152.135787964
Episode 0 Step 194 Action [[ 0.46830238  0.44703365  0.44801104  0.57941753  0.64924513  0.41625447
   0.61268189  0.3989384 ]] Reward -5458.48209784 Loss 176.780029297
Episode 0 Step 195 Action [[ 0.59775455  0.43422927  0.51057673  0.45046281  0.58387364  0.56932222
   0.70424455  0.35357427]] Reward -5489.19086666 Loss 152.593414307
Episode 0 Step 196 Action [[ 0.30253888  0.54869467  0.64573501  0.51929903  0.60564173  0.6186214
   0.37971324  0.60796095]] Reward -5521.62483728 Loss 40.4557304382
Episode 0 Step 197 Action [[ 0.34652938  0.61744617  0.57635549  0.60252139  0.67418038  0.52095151
   0.46285843  0.42508041]] Reward -5553.62080306 Loss 306.029174805
Episode 0 Step 198 Action [[ 0.4636332   0.58256256  0.5257034   0.68511334  0.35248094  0.56613622
   0.48684098  0.45512412]] Reward -5581.16261996 Loss 1311.40454102
Episode 0 Step 199 Action [[ 0.35890306  0.41825356  0.44023473  0.2709554   0.56148474  0.4154172
   0.48945195  0.66813976]] Reward -5609.79964212 Loss 2139.18164062
Episode 0 Step 200 Action [[ 0.60718646  0.49885675  0.45971704  0.61035871  0.58964933  0.4363554
   0.36618091  0.56133036]] Reward -5638.01131582 Loss 263.640075684
Episode 0 Step 201 Action [[ 0.40378213  0.58653474  0.58298953  0.28487793  0.53582444  0.43163298
   0.52485948  0.70965822]] Reward -5666.56321514 Loss 452.201385498
Episode 0 Step 202 Action [[ 0.58901755  0.57350989  0.66458151  0.50986826  0.35550006  0.60849144
   0.62635259  0.4679589 ]] Reward -5693.94736378 Loss 1651.09094238
Episode 0 Step 203 Action [[ 0.48502584  0.47549133  0.44698845  0.46061988  0.54249971  0.35919971
   0.66044274  0.53872563]] Reward -5719.6782135 Loss 371.182312012
Episode 0 Step 204 Action [[ 0.40498318  0.55121812  0.45937687  0.34171761  0.31839038  0.57309391
   0.47025595  0.53150637]] Reward -5745.44896728 Loss 325.73336792
Episode 0 Step 205 Action [[ 0.39212074  0.37520302  0.4263653   0.52862571  0.58907436  0.71363446
   0.57477393  0.50846346]] Reward -5777.01446923 Loss 1087.65234375
Episode 0 Step 206 Action [[ 0.42842862  0.63657948  0.52066741  0.45725639  0.42615294  0.52464394
   0.63575818  0.4622251 ]] Reward -5804.12942594 Loss 145.101547241
Episode 0 Step 207 Action [[ 0.55674198  0.30806882  0.49222542  0.29487415  0.46381795  0.58668058
   0.55531729  0.28935439]] Reward -5831.80005885 Loss 476.858764648
Episode 0 Step 208 Action [[ 0.67203991  0.47287346  0.57028558  0.40109226  0.51343337  0.40943403
   0.52218271  0.45582101]] Reward -5857.26523228 Loss 846.352600098
Episode 0 Step 209 Action [[ 0.50462003  0.45405874  0.39909775  0.54687806  0.38925664  0.42475684
   0.57773872  0.58911547]] Reward -5880.28242964 Loss 245.419525146
Episode 0 Step 210 Action [[ 0.42186474  0.3693068   0.4403309   0.56003878  0.53581032  0.4850503
   0.60397183  0.51117966]] Reward -5907.3815621 Loss 191.816696167
Episode 0 Step 211 Action [[ 0.2747209   0.50909892  0.57607393  0.41381667  0.29898152  0.41574915
   0.58188962  0.64811532]] Reward -5930.66473252 Loss 1205.14916992
Episode 0 Step 212 Action [[ 0.39467112  0.48888415  0.36038011  0.63029352  0.53717941  0.49855129
   0.43830373  0.51667887]] Reward -5958.27379265 Loss 2886.8046875
Episode 0 Step 213 Action [[ 0.41140347  0.58319678  0.51188394  0.58355601  0.5082414   0.56515528
   0.38851116  0.51628782]] Reward -5988.17059123 Loss 1740.26000977
Episode 0 Step 214 Action [[ 0.46140176  0.58211905  0.50949468  0.53311859  0.6054475   0.45902186
   0.39588857  0.47246111]] Reward -6018.23292212 Loss 2070.79394531
Episode 0 Step 215 Action [[ 0.67234769  0.50697006  0.63157556  0.54016946  0.47902013  0.64533331
   0.30083891  0.47432251]] Reward -6049.43996834 Loss 4031.67333984
Episode 0 Step 216 Action [[ 0.59916319  0.47323199  0.25634386  0.38791211  0.50134659  0.4944737
   0.43603549  0.54376979]] Reward -6077.34926319 Loss 1146.10083008
Episode 0 Step 217 Action [[ 0.5342823   0.68288793  0.65096726  0.4549642   0.47926671  0.30474315
   0.54674424  0.34815472]] Reward -6102.6917075 Loss 1738.11816406
Episode 0 Step 218 Action [[ 0.41168749  0.42965562  0.44952184  0.56787947  0.54195733  0.46857747
   0.39532254  0.67380499]] Reward -6130.33833315 Loss 5359.54003906
Episode 0 Step 219 Action [[ 0.49150935  0.62851314  0.51916321  0.52704956  0.38912478  0.36934527
   0.52985607  0.80795581]] Reward -6154.96431262 Loss 593.049682617
Episode 0 Step 220 Action [[ 0.54657412  0.41844657  0.35924796  0.50597971  0.42073969  0.23208385
   0.44540668  0.59691935]] Reward -6176.70867644 Loss 1640.91479492
Episode 0 Step 221 Action [[ 0.379121    0.45900457  0.597699    0.66057378  0.59062418  0.20799795
   0.59248583  0.63861249]] Reward -6201.84617689 Loss 1665.32592773
Episode 0 Step 222 Action [[ 0.42824705  0.58741339  0.49244833  0.45433482  0.41937785  0.54658432
   0.56636251  0.34139828]] Reward -6230.5395874 Loss 66.4367370605
Episode 0 Step 223 Action [[ 0.25295545  0.59519486  0.42031759  0.43935118  0.45441553  0.35612583
   0.55638252  0.37920247]] Reward -6255.96228637 Loss 638.430786133
Episode 0 Step 224 Action [[ 0.42862743  0.49219061  0.42024241  0.51968557  0.3711253   0.45979846
   0.54020796  0.38954988]] Reward -6280.95126471 Loss 164.667907715
Episode 0 Step 225 Action [[ 0.62343527  0.40078754  0.5534135   0.29452523  0.40110486  0.4439387
   0.43738731  0.53032537]] Reward -6306.42478125 Loss 288.691131592
Episode 0 Step 226 Action [[ 0.51222123  0.45904028  0.26235457  0.4263216   0.60348951  0.50720008
   0.31291321  0.44938515]] Reward -6334.69735464 Loss 213.076904297
Episode 0 Step 227 Action [[ 0.60748692  0.44452051  0.54763674  0.44671579  0.63489339  0.38005295
   0.49980262  0.61176159]] Reward -6362.0924241 Loss 173.982940674
Episode 0 Step 228 Action [[ 0.63371823  0.43341181  0.28055725  0.35857334  0.39502331  0.48696825
   0.47852404  0.22928525]] Reward -6386.36030744 Loss 605.276000977
Episode 0 Step 229 Action [[ 0.53178021  0.50272155  0.53811028  0.36610846  0.23132151  0.39569668
   0.51763538  0.43925255]] Reward -6406.90144785 Loss 67.7318115234
Episode 0 Step 230 Action [[ 0.40488714  0.52614725  0.47131404  0.3516093   0.36831283  0.52169055
   0.45962282  0.55975122]] Reward -6431.52002481 Loss 491.879333496
Episode 0 Step 231 Action [[ 0.41064064  0.41594248  0.40516557  0.54976296  0.52268131  0.44813855
   0.46698522  0.53025875]] Reward -6456.72920065 Loss 513.738220215
Episode 0 Step 232 Action [[ 0.41279496  0.43020012  0.53019079  0.32573052  0.33782635  0.25360418
   0.43475418  0.55106811]] Reward -6476.70572147 Loss 32.4791526794
Episode 0 Step 233 Action [[ 0.42536493  0.58021231  0.46632495  0.64277132  0.60886791  0.47708046
   0.45862693  0.57831296]] Reward -6504.82458248 Loss 496.06640625
Episode 0 Step 234 Action [[ 0.43975709  0.50154734  0.48396883  0.48258825  0.69703375  0.48886684
   0.35457233  0.55091774]] Reward -6535.63628878 Loss 144.177337646
Episode 0 Step 235 Action [[ 0.51091824  0.3116093   0.49357543  0.60799165  0.63221807  0.54794695
   0.41389017  0.56099025]] Reward -6565.89067762 Loss 165.678771973
Episode 0 Step 236 Action [[ 0.27308301  0.5017994   0.3901134   0.55042668  0.63378377  0.45327049
   0.44778556  0.45965492]] Reward -6595.50077881 Loss 373.507873535
Episode 0 Step 237 Action [[ 0.32053139  0.56601887  0.41490428  0.4038063   0.40274489  0.4134436
   0.52809001  0.48539611]] Reward -6620.90884159 Loss 121.32131958
Episode 0 Step 238 Action [[ 0.54629525  0.60818418  0.39021633  0.45970482  0.38950743  0.41591274
   0.48438038  0.47672165]] Reward -6645.537358 Loss 81.1736526489
Episode 0 Step 239 Action [[ 0.45793496  0.45740425  0.35425339  0.57002118  0.6101046   0.44520191
   0.55065689  0.48134307]] Reward -6673.77608259 Loss 174.52331543
Episode 0 Step 240 Action [[ 0.46939117  0.70994339  0.6004391   0.49241489  0.26936288  0.40694619
   0.49229761  0.59697911]] Reward -6697.47815026 Loss 41.9110221863
Episode 0 Step 241 Action [[ 0.45134002  0.40276214  0.47695794  0.39920061  0.43937952  0.49480319
   0.54245716  0.46377656]] Reward -6724.15350963 Loss 93.0845184326
Episode 0 Step 242 Action [[ 0.35253608  0.43369398  0.53692319  0.49184438  0.63179952  0.48676552
   0.43801433  0.5617537 ]] Reward -6753.80115285 Loss 137.704467773
Episode 0 Step 243 Action [[ 0.39871501  0.54623288  0.35597367  0.64661003  0.41429227  0.41361252
   0.56828822  0.44719335]] Reward -6778.36002441 Loss 34.0792541504
Episode 0 Step 244 Action [[ 0.41279989  0.55800812  0.49145881  0.51425316  0.40014947  0.43430034
   0.28059207  0.49285606]] Reward -6804.29623593 Loss 64.740524292
Episode 0 Step 245 Action [[ 0.35688921  0.30905571  0.48583742  0.46637793  0.49356972  0.32826987
   0.53512166  0.54486644]] Reward -6829.23847322 Loss 112.44329834
Episode 0 Step 246 Action [[ 0.56204955  0.49625104  0.60295513  0.50179814  0.52520816  0.36912183
   0.62951029  0.54275223]] Reward -6856.01485913 Loss 49.2979354858
Episode 0 Step 247 Action [[ 0.67676422  0.49071662  0.42339328  0.38720742  0.63183457  0.58231775
   0.38103698  0.52184598]] Reward -6887.62097258 Loss 36.9562454224
Episode 0 Step 248 Action [[ 0.52536731  0.5137679   0.43411565  0.5103347   0.5272433   0.56936583
   0.54046296  0.55271052]] Reward -6916.80948741 Loss 72.3021392822
Episode 0 Step 249 Action [[ 0.54447836  0.49443205  0.52765331  0.436387    0.56764985  0.63398813
   0.43782443  0.43517783]] Reward -6948.14505694 Loss 39.7899093628
Episode 0 Step 250 Action [[ 0.42223399  0.59460821  0.56411838  0.447932    0.35468382  0.46959473
   0.7255762   0.41288325]] Reward -6973.27764421 Loss 38.8235931396
Episode 0 Step 251 Action [[ 0.46124263  0.55964689  0.53698605  0.5223638   0.59250513  0.47378513
   0.49382301  0.58435274]] Reward -7002.19042881 Loss 53.3477363586
Episode 0 Step 252 Action [[ 0.40878432  0.55551548  0.48009025  0.64004916  0.495706    0.39593776
   0.48886548  0.47087611]] Reward -7028.25230472 Loss 27.8674468994
Episode 0 Step 253 Action [[ 0.5445064   0.49717999  0.50496612  0.67547413  0.39364333  0.44037227
   0.55508051  0.44709807]] Reward -7054.03018399 Loss 133.453201294
Episode 0 Step 254 Action [[ 0.3082065   0.73921572  0.51082404  0.55044998  0.47985575  0.66790564
   0.55341232  0.2956707 ]] Reward -7086.65743333 Loss 219.865905762
Episode 0 Step 255 Action [[ 0.46846725  0.51698807  0.65277194  0.50635163  0.41338678  0.43679265
   0.45145543  0.3036406 ]] Reward -7113.80162234 Loss 68.5413742065
Episode 0 Step 256 Action [[ 0.53032331  0.69184056  0.36046709  0.64079842  0.44957226  0.46524513
   0.4391445   0.65781771]] Reward -7141.47857875 Loss 79.7493591309
Episode 0 Step 257 Action [[ 0.6528421   0.50563049  0.5474479   0.30085201  0.38460178  0.35050978
   0.46837136  0.53675361]] Reward -7166.52331422 Loss 260.573974609
Episode 0 Step 258 Action [[ 0.52832591  0.43108475  0.62126938  0.51181559  0.52449606  0.52429024
   0.52602871  0.52313474]] Reward -7195.58461275 Loss 133.0599823
Episode 0 Step 259 Action [[ 0.68915968  0.50026842  0.49175192  0.41737837  0.53308622  0.60244355
   0.40279013  0.53608095]] Reward -7225.99202132 Loss 25.5069828033
Episode 0 Step 260 Action [[ 0.45925375  0.42897259  0.40062701  0.4837313   0.455879    0.41301842
   0.44132689  0.60970033]] Reward -7251.0248568 Loss 106.693122864
Episode 0 Step 261 Action [[ 0.5763018   0.4951614   0.37229413  0.31357818  0.44153838  0.47442629
   0.41545742  0.4380562 ]] Reward -7276.9647478 Loss 96.8428192139
Episode 0 Step 262 Action [[ 0.49188475  0.51814854  0.53065978  0.50030193  0.41707524  0.47342143
   0.45775097  0.58270478]] Reward -7302.23140858 Loss 19.4895744324
Episode 0 Step 263 Action [[ 0.58782822  0.66174707  0.57558876  0.68115985  0.5934099   0.2990951
   0.4958195   0.369958  ]] Reward -7328.38323672 Loss 107.473587036
Episode 0 Step 264 Action [[ 0.45902968  0.7278336   0.49655194  0.500869    0.41431229  0.39877412
   0.49772256  0.48934162]] Reward -7354.32257396 Loss 120.747436523
Episode 0 Step 265 Action [[ 0.46266569  0.41354507  0.59910916  0.74389993  0.55497594  0.31014359
   0.50422782  0.44334699]] Reward -7380.4093562 Loss 71.0688323975
Episode 0 Step 266 Action [[ 0.48318347  0.44163681  0.37387932  0.4608333   0.63659603  0.38519428
   0.42965171  0.37468012]] Reward -7409.74934177 Loss 25.9887466431
Episode 0 Step 267 Action [[ 0.63081504  0.43224802  0.31911818  0.443572    0.54313678  0.53911622
   0.57135957  0.69244584]] Reward -7439.4051399 Loss 100.792182922
Episode 0 Step 268 Action [[ 0.42469718  0.51544575  0.58536708  0.35158814  0.37870601  0.41844767
   0.36832774  0.49290836]] Reward -7464.65658401 Loss 102.800415039
Episode 0 Step 269 Action [[ 0.66091448  0.71086499  0.52710384  0.54194259  0.60844122  0.60399101
   0.49445509  0.60297839]] Reward -7496.57156969 Loss 90.4953460693
Episode 0 Step 270 Action [[ 0.3583815   0.63978011  0.36159522  0.66904166  0.54873846  0.51627031
   0.51743642  0.49324965]] Reward -7525.65531215 Loss 73.5753326416
Episode 0 Step 271 Action [[ 0.46953371  0.36645796  0.27997676  0.48968485  0.45804522  0.27888889
   0.55449274  0.34439351]] Reward -7548.98259604 Loss 56.9094467163
Episode 0 Step 272 Action [[ 0.51031708  0.6055255   0.37517216  0.43008735  0.55603201  0.47929184
   0.54613592  0.39597321]] Reward -7578.15052356 Loss 41.2023086548
Episode 0 Step 273 Action [[ 0.67671835  0.67624104  0.73046889  0.51693531  0.52916852  0.35624275
   0.57357908  0.60240727]] Reward -7605.53990534 Loss 17.2335472107
Episode 0 Step 274 Action [[ 0.42237779  0.35942477  0.49641898  0.54096485  0.31357187  0.59570427
   0.60885254  0.47545932]] Reward -7631.75113988 Loss 110.428970337
Episode 0 Step 275 Action [[ 0.56555845  0.31157438  0.41256447  0.47502384  0.57143013  0.45682207
   0.45124141  0.44577262]] Reward -7659.8184729 Loss 480.477905273
Episode 0 Step 276 Action [[ 0.63522675  0.48804467  0.60337443  0.45151627  0.56465442  0.53835594
   0.41690713  0.57945535]] Reward -7690.06479255 Loss 1585.93432617
Episode 0 Step 277 Action [[ 0.43996386  0.4073008   0.48198987  0.56148489  0.37775901  0.35457151
   0.60661926  0.24300403]] Reward -7713.10971122 Loss 914.543518066
Episode 0 Step 278 Action [[ 0.48282205  0.36074328  0.44224976  0.47059289  0.53825557  0.41263699
   0.25960542  0.50216654]] Reward -7740.01034317 Loss 76.1401519775
Episode 0 Step 279 Action [[ 0.48397659  0.62622569  0.38473603  0.59318689  0.38178179  0.50399927
   0.43164132  0.61573149]] Reward -7766.24989552 Loss 143.106781006
Episode 0 Step 280 Action [[ 0.48154951  0.61670329  0.58081378  0.72372295  0.50079951  0.63181358
   0.43793078  0.61513683]] Reward -7797.69123156 Loss 589.96496582
Episode 0 Step 281 Action [[ 0.53834583  0.5312421   0.49528007  0.44793012  0.64984201  0.63803094
   0.5220775   0.56584635]] Reward -7832.23407617 Loss 816.270629883
Episode 0 Step 282 Action [[ 0.4430161   0.81469368  0.37888664  0.66390118  0.53858852  0.57534755
   0.45268423  0.5021214 ]] Reward -7863.6501353 Loss 524.412109375
Episode 0 Step 283 Action [[ 0.35303444  0.53300035  0.47649529  0.46457549  0.45829694  0.4808376
   0.41456144  0.49863407]] Reward -7892.12482294 Loss 36.2895851135
Episode 0 Step 284 Action [[ 0.40436334  0.43292442  0.61095532  0.30318942  0.37813806  0.55789316
   0.32752728  0.47630009]] Reward -7920.06942291 Loss 181.70703125
Episode 0 Step 285 Action [[ 0.49444826  0.64668687  0.4856072   0.41560026  0.42031207  0.67080243
   0.53554005  0.54852518]] Reward -7949.73478001 Loss 529.353271484
Episode 0 Step 286 Action [[ 0.36148996  0.47515255  0.55651817  0.44919528  0.51149385  0.38797379
   0.41533867  0.66417801]] Reward -7975.54406374 Loss 528.617797852
Episode 0 Step 287 Action [[ 0.46106792  0.55515797  0.54731418  0.60330639  0.58019976  0.66296901
   0.55507591  0.54803628]] Reward -8007.36039198 Loss 981.265686035
Episode 0 Step 288 Action [[ 0.56178249  0.34380795  0.48258573  0.50039861  0.41662068  0.57588453
   0.45992773  0.43722678]] Reward -8034.80938735 Loss 1331.24414062
Episode 0 Step 289 Action [[ 0.56197049  0.35823024  0.56991916  0.65183884  0.50079632  0.5119946
   0.41939948  0.48531189]] Reward -8062.96212959 Loss 957.943359375
Episode 0 Step 290 Action [[ 0.61388951  0.43832722  0.47436058  0.3505195   0.29224075  0.63080873
   0.58987019  0.14354842]] Reward -8090.25558795 Loss 35.6327285767
Episode 0 Step 291 Action [[ 0.43185476  0.56816889  0.44578096  0.51341304  0.49889064  0.64126165
   0.40818521  0.59176589]] Reward -8120.66245295 Loss 470.634918213
Episode 0 Step 292 Action [[ 0.51423061  0.41345897  0.50615613  0.5411212   0.55786215  0.50113846
   0.5833015   0.44376096]] Reward -8149.48671501 Loss 2291.171875
Episode 0 Step 293 Action [[ 0.53189292  0.54392811  0.55174593  0.66434521  0.56567646  0.54211627
   0.59566606  0.29259795]] Reward -8179.8859771 Loss 4716.44628906
Episode 0 Step 294 Action [[ 0.370524    0.36803997  0.47511357  0.46732778  0.5047981   0.66125141
   0.55908613  0.48849311]] Reward -8211.34334264 Loss 211.905075073
Episode 0 Step 295 Action [[ 0.45971455  0.51075547  0.38044314  0.46571779  0.48407552  0.23874586
   0.48714351  0.524159  ]] Reward -8234.93995349 Loss 2639.39404297
Episode 0 Step 296 Action [[ 0.56051028  0.35587386  0.51720788  0.57361018  0.32349412  0.57437246
   0.44321531  0.40651636]] Reward -8261.13292908 Loss 5251.10449219
Episode 0 Step 297 Action [[ 0.45818029  0.54371686  0.58379834  0.55339188  0.46093537  0.49618111
   0.44644387  0.40481965]] Reward -8289.43010319 Loss 517.337646484
Episode 0 Step 298 Action [[ 0.44919182  0.44038988  0.47463316  0.33984468  0.55029474  0.72984864
   0.54912694  0.55295554]] Reward -8322.72341248 Loss 2512.00268555
Episode 0 Step 299 Action [[ 0.49727378  0.42751446  0.31875832  0.59892015  0.40626066  0.49052099
   0.54652375  0.45922722]] Reward -8348.00344762 Loss 11767.3671875
Episode 0 Step 300 Action [[ 0.5190468   0.51336059  0.43975611  0.45862773  0.66449755  0.44772779
   0.53425922  0.34480527]] Reward -8378.16493927 Loss 6008.75634766
Episode 0 Step 301 Action [[ 0.50343754  0.29983347  0.58490147  0.44652519  0.49810902  0.43154975
   0.4062912   0.49884896]] Reward -8404.7417995 Loss 8062.07519531
Episode 0 Step 302 Action [[ 0.4472201   0.55971895  0.52689028  0.53336795  0.57488075  0.44663979
   0.4789954   0.67160105]] Reward -8433.2482859 Loss 29076.6835938
Episode 0 Step 303 Action [[ 0.25789595  0.49951104  0.53754122  0.41342696  0.52891614  0.5905921
   0.47757626  0.36623207]] Reward -8463.48262806 Loss 2675.23852539
Episode 0 Step 304 Action [[ 0.53669427  0.34938196  0.52885675  0.50394457  0.54456208  0.64431817
   0.38323028  0.39359631]] Reward -8493.99941636 Loss 25992.5820312
Episode 0 Step 305 Action [[ 0.40225106  0.49433865  0.44159519  0.5857299   0.47193063  0.493911
   0.46724866  0.6066647 ]] Reward -8521.10925343 Loss 9645.16894531
Episode 0 Step 306 Action [[ 0.24467996  0.4831831   0.6477826   0.17803526  0.58138926  0.38302851
   0.4530936   0.33382309]] Reward -8549.2439647 Loss 10836.9375
Episode 0 Step 307 Action [[ 0.60226135  0.4281246   0.59649979  0.58977248  0.36499306  0.58517185
   0.52062871  0.50385788]] Reward -8575.11781892 Loss 5605.34814453
Episode 0 Step 308 Action [[ 0.52447421  0.62084853  0.47992831  0.45998372  0.52877648  0.35877351
   0.30262961  0.48344429]] Reward -8601.04437792 Loss 12758.4306641
Episode 0 Step 309 Action [[ 0.42685047  0.33248881  0.40451664  0.44087624  0.53472881  0.35033485
   0.50815615  0.52962777]] Reward -8625.86442124 Loss 2147.45678711
Episode 0 Step 310 Action [[ 0.56867918  0.47015237  0.59667611  0.44463495  0.48932707  0.47981921
   0.42604051  0.38519205]] Reward -8652.93711966 Loss 12095.0039062
Episode 0 Step 311 Action [[ 0.45230409  0.56627255  0.42143205  0.55651689  0.65428774  0.55788284
   0.45503848  0.4860843 ]] Reward -8683.88763982 Loss 205.724121094
Episode 0 Step 312 Action [[ 0.44909164  0.34418818  0.42231079  0.63997455  0.52177671  0.52068797
   0.40582733  0.48321193]] Reward -8711.79803479 Loss 11028.3242188
Episode 0 Step 313 Action [[ 0.3793877   0.60186396  0.39684291  0.41872079  0.19367804  0.49902644
   0.29401861  0.50743286]] Reward -8735.20828528 Loss 26.7435684204
Episode 0 Step 314 Action [[ 0.53947184  0.44884108  0.52319149  0.40099332  0.48995301  0.42194881
   0.51573068  0.31067438]] Reward -8761.70048855 Loss 10918.4462891
Episode 0 Step 315 Action [[ 0.54850606  0.58043324  0.514812    0.45738186  0.51868393  0.63159937
   0.40855925  0.55349877]] Reward -8792.16691498 Loss 1237.43103027
Episode 0 Step 316 Action [[ 0.44848213  0.50486396  0.55634061  0.52138227  0.69296479  0.31980354
   0.46562074  0.42362758]] Reward -8820.11813299 Loss 7460.83984375
Episode 0 Step 317 Action [[ 0.52005468  0.49118551  0.46791043  0.36646276  0.46373201  0.55012333
   0.51583194  0.54114868]] Reward -8848.06687537 Loss 242.632598877
Episode 0 Step 318 Action [[ 0.42007042  0.59794778  0.43274723  0.49985025  0.61370841  0.40135617
   0.4803612   0.23607461]] Reward -8875.65800697 Loss 7516.34277344
Episode 0 Step 319 Action [[ 0.50028966  0.39651159  0.24321089  0.42101789  0.5979089   0.71966118
   0.20646194  0.53339689]] Reward -8907.5455267 Loss 38.974822998
Episode 0 Step 320 Action [[ 0.57434318  0.5395622   0.47677981  0.64843932  0.40032852  0.43701918
   0.50502627  0.45732235]] Reward -8932.14535764 Loss 6434.22363281
Episode 0 Step 321 Action [[ 0.66743397  0.5315356   0.53928237  0.42245126  0.51432569  0.70515476
   0.55612709  0.63347924]] Reward -8964.39720912 Loss 103.354354858
Episode 0 Step 322 Action [[ 0.47331011  0.58819063  0.43806857  0.50272374  0.57806833  0.2990348
   0.43845531  0.39415066]] Reward -8990.22143262 Loss 4796.68652344
Episode 0 Step 323 Action [[ 0.53485494  0.71609313  0.43503245  0.36461902  0.54969772  0.25352138
   0.60792309  0.46842483]] Reward -9015.26780975 Loss 191.084747314
Episode 0 Step 324 Action [[ 0.60910341  0.45958741  0.37775216  0.5586044   0.36663628  0.54835582
   0.47312948  0.48909208]] Reward -9040.65504263 Loss 3201.28393555
Episode 0 Step 325 Action [[ 0.34501834  0.4459116   0.63751381  0.42760664  0.51514591  0.46335521
   0.61799048  0.46610328]] Reward -9068.43127666 Loss 273.217193604
Episode 0 Step 326 Action [[ 0.44005405  0.43886911  0.49108741  0.42553119  0.50729627  0.47610262
   0.41793627  0.3866631 ]] Reward -9095.48902678 Loss 3016.44995117
Episode 0 Step 327 Action [[ 0.51515156  0.51585255  0.62085806  0.67704171  0.6215047   0.53330095
   0.44004472  0.64996201]] Reward -9125.92740719 Loss 45.4877662659
Episode 0 Step 328 Action [[ 0.65207449  0.39337296  0.45687927  0.5641112   0.34842875  0.41571608
   0.63969017  0.53589864]] Reward -9149.93966907 Loss 1893.78137207
Episode 0 Step 329 Action [[ 0.4805291   0.38173782  0.40579438  0.52121418  0.40967068  0.44150579
   0.62091367  0.40432344]] Reward -9175.48913625 Loss 507.492370605
Episode 0 Step 330 Action [[ 0.30345356  0.49239257  0.52282943  0.44316026  0.4482887   0.36244183
   0.70550886  0.53807142]] Reward -9200.99182323 Loss 2523.23535156
Episode 0 Step 331 Action [[ 0.5630899   0.40249628  0.51050488  0.49793595  0.54057407  0.52093916
   0.54355509  0.33562182]] Reward -9229.95107962 Loss 985.210571289
Episode 0 Step 332 Action [[ 0.49763302  0.5392903   0.49485719  0.24895236  0.42147505  0.48069899
   0.43096234  0.5950408 ]] Reward -9256.57970691 Loss 1284.9407959
Episode 0 Step 333 Action [[ 0.48479217  0.55182305  0.53266078  0.35892482  0.63891746  0.54864865
   0.46604237  0.61592845]] Reward -9286.94613146 Loss 3563.30322266
Episode 0 Step 334 Action [[ 0.52932759  0.55795937  0.64044739  0.54740774  0.35533517  0.50821969
   0.29451587  0.62445044]] Reward -9311.74629529 Loss 905.939819336
Episode 0 Step 335 Action [[ 0.41023892  0.46591695  0.37219759  0.47214922  0.35612735  0.56788526
   0.4245524   0.48302374]] Reward -9337.23075469 Loss 1797.66320801
Episode 0 Step 336 Action [[ 0.53824143  0.43626877  0.64476851  0.4294146   0.54528448  0.61216268
   0.51236492  0.68383974]] Reward -9367.55989634 Loss 38.2906341553
Episode 0 Step 337 Action [[ 0.33660987  0.66010569  0.51357074  0.49233783  0.44086714  0.49647846
   0.46509842  0.47094026]] Reward -9394.24475935 Loss 1382.19445801
Episode 0 Step 338 Action [[ 0.26744807  0.52680276  0.61482789  0.57091299  0.58944885  0.78806269
   0.45499699  0.50185435]] Reward -9428.56523611 Loss 596.943725586
Episode 0 Step 339 Action [[ 0.49424258  0.47403329  0.45806349  0.46988053  0.5810093   0.27032027
   0.50649721  0.65639796]] Reward -9453.83696519 Loss 1136.66503906
Episode 0 Step 340 Action [[ 0.28460838  0.35347475  0.44908651  0.40325875  0.50358681  0.50301019
   0.51218427  0.74424165]] Reward -9481.30772998 Loss 468.874420166
Episode 0 Step 341 Action [[ 0.46329713  0.47575459  0.5696782   0.4020235   0.4945726   0.45373329
   0.54047747  0.49369017]] Reward -9508.0333541 Loss 574.263549805
Episode 0 Step 342 Action [[ 0.41411704  0.45822125  0.56875421  0.57042175  0.60556182  0.57158141
   0.38318625  0.3067094 ]] Reward -9538.30163783 Loss 320.485961914
Episode 0 Step 343 Action [[ 0.58513991  0.53011163  0.7315942   0.47263515  0.53754535  0.44670474
   0.39599871  0.48825186]] Reward -9566.61631967 Loss 634.51159668
Episode 0 Step 344 Action [[ 0.41027671  0.45431458  0.39338183  0.53801822  0.27535546  0.56143545
   0.5445417   0.37332998]] Reward -9591.15015089 Loss 73.8271179199
Episode 0 Step 345 Action [[ 0.41857772  0.44574528  0.4141234   0.51927531  0.31476327  0.39332219
   0.59295078  0.55091489]] Reward -9613.85789564 Loss 231.242340088
Episode 0 Step 346 Action [[ 0.32127652  0.61983394  0.38297003  0.2312257   0.37367477  0.38282725
   0.54196131  0.42613632]] Reward -9637.89998627 Loss 342.897644043
Episode 0 Step 347 Action [[ 0.44653816  0.65454442  0.51312603  0.37682011  0.49726253  0.49159985
   0.48217234  0.48647191]] Reward -9665.02076832 Loss 113.744239807
Episode 0 Step 348 Action [[ 0.49958988  0.61670917  0.46318917  0.54168116  0.43084405  0.35287296
   0.46199056  0.3176251 ]] Reward -9688.1296855 Loss 336.782714844
Episode 0 Step 349 Action [[ 0.51245626  0.54945758  0.4283654   0.39317594  0.40038883  0.61650479
   0.40630392  0.45097765]] Reward -9715.60135916 Loss 41.4880218506
Episode 0 Step 350 Action [[ 0.42259709  0.39790167  0.50385004  0.45992895  0.31161991  0.45259313
   0.4044965   0.45417479]] Reward -9738.27888025 Loss 381.399810791
Episode 0 Step 351 Action [[ 0.2795037   0.60106584  0.54457602  0.52977612  0.6333232   0.47220225
   0.65147084  0.48829158]] Reward -9767.66625852 Loss 112.811889648
Episode 0 Step 352 Action [[ 0.58622914  0.45861862  0.39681348  0.47651179  0.59929529  0.59197749
   0.41542513  0.5042443 ]] Reward -9798.02193587 Loss 241.762939453
Episode 0 Step 353 Action [[ 0.31054058  0.511645    0.56191575  0.42247819  0.39488284  0.54516585
   0.58473108  0.61117408]] Reward -9824.87635762 Loss 30.2858734131
Episode 0 Step 354 Action [[ 0.48452871  0.77652437  0.45030455  0.44028489  0.39419117  0.46996402
   0.49002761  0.54669977]] Reward -9850.57294827 Loss 217.243225098
Episode 0 Step 355 Action [[ 0.48165477  0.61237429  0.47734939  0.55180664  0.50233927  0.35715304
   0.61541708  0.56080299]] Reward -9875.73443074 Loss 17.9413433075
Episode 0 Step 356 Action [[ 0.49194375  0.55061024  0.57610084  0.43585471  0.59490002  0.30184227
   0.51996463  0.45182476]] Reward -9902.12936241 Loss 224.541320801
Episode 0 Step 357 Action [[ 0.3773665   0.61419084  0.60003785  0.57697257  0.47003494  0.54668791
   0.56235054  0.59033838]] Reward -9930.64150157 Loss 63.7621116638
Episode 0 Step 358 Action [[ 0.48098181  0.47374354  0.76889597  0.51704839  0.44198155  0.54719069
   0.35043382  0.2018104 ]] Reward -9959.22981644 Loss 80.9171676636
Episode 0 Step 359 Action [[ 0.54979131  0.59572829  0.39755302  0.39498229  0.50213462  0.27127256
   0.44603022  0.38258612]] Reward -9983.54966487 Loss 53.0575256348
Episode 0 Step 360 Action [[ 0.41005654  0.38638638  0.53856872  0.4229071   0.45101365  0.43655857
   0.54563734  0.45404326]] Reward -10009.0973991 Loss 81.1588745117
Episode 0 Step 361 Action [[ 0.45173244  0.31946388  0.61998813  0.56513997  0.45402721  0.51885634
   0.40059046  0.55659557]] Reward -10035.8766801 Loss 76.2867736816
Episode 0 Step 362 Action [[ 0.38700298  0.28931516  0.61675911  0.59941788  0.39473314  0.57274812
   0.38681071  0.43884748]] Reward -10062.9984961 Loss 57.1299705505
Episode 0 Step 363 Action [[ 0.44906798  0.51421665  0.5500952   0.4618578   0.47827198  0.59149871
   0.5067708   0.67624839]] Reward -10092.9067989 Loss 51.1480865479
Episode 0 Step 364 Action [[ 0.39979522  0.4492077   0.45226728  0.45545789  0.58791436  0.29800835
   0.66932787  0.49502251]] Reward -10118.8758551 Loss 47.1831970215
Episode 0 Step 365 Action [[ 0.28859156  0.44796367  0.57294691  0.46401923  0.45085784  0.38186507
   0.59109344  0.44806691]] Reward -10144.0537011 Loss 67.5562210083
Episode 0 Step 366 Action [[ 0.60724821  0.43769492  0.59517013  0.45843926  0.40815777  0.44174105
   0.51942706  0.36047461]] Reward -10169.3841306 Loss 44.0889167786
Episode 0 Step 367 Action [[ 0.5688116   0.43284997  0.46717929  0.32267478  0.43120419  0.53939201
   0.38780769  0.53848346]] Reward -10196.3057244 Loss 73.0639266968
Episode 0 Step 368 Action [[ 0.35031432  0.61992369  0.54959426  0.41550313  0.34625901  0.37150998
   0.4238947   0.65655236]] Reward -10218.9749632 Loss 29.4306411743
Episode 0 Step 369 Action [[ 0.4183581   0.300529    0.52712089  0.55524049  0.57062424  0.53351141
   0.41535489  0.63412577]] Reward -10247.0995555 Loss 52.8239555359
Episode 0 Step 370 Action [[ 0.4182022   0.42555646  0.25204065  0.28044924  0.43451523  0.55195904
   0.29234247  0.61441325]] Reward -10273.4487892 Loss 18.720085144
Episode 0 Step 371 Action [[ 0.50140798  0.52932804  0.35963786  0.62855768  0.43555881  0.4986814
   0.4263869   0.38533776]] Reward -10298.6093768 Loss 44.9714202881
Episode 0 Step 372 Action [[ 0.52751672  0.65425326  0.4020976   0.71620306  0.533477    0.40714932
   0.27582532  0.47240302]] Reward -10325.4579988 Loss 37.8825531006
Episode 0 Step 373 Action [[ 0.53260314  0.41249064  0.66828964  0.49984054  0.59302281  0.45686371
   0.53687932  0.54096224]] Reward -10355.4614152 Loss 25.7835197449
Episode 0 Step 374 Action [[ 0.37226924  0.60290486  0.46756355  0.50333319  0.48570394  0.26419497
   0.60987441  0.51969795]] Reward -10380.0903024 Loss 23.7641944885
Episode 0 Step 375 Action [[ 0.35070832  0.46308218  0.49890641  0.48155117  0.46803866  0.31920901
   0.32576423  0.73095531]] Reward -10404.8795708 Loss 32.9647674561
Episode 0 Step 376 Action [[ 0.4577929   0.44944082  0.44973703  0.36771247  0.33418732  0.53850932
   0.66601624  0.50850169]] Reward -10430.7365004 Loss 50.0112609863
Episode 0 Step 377 Action [[ 0.43146347  0.29894735  0.2968517   0.5414191   0.36217937  0.49240285
   0.28878168  0.27030974]] Reward -10454.6556018 Loss 25.439956665
Episode 0 Step 378 Action [[ 0.58421474  0.56322312  0.50479236  0.44269029  0.50084759  0.49966221
   0.56686808  0.50302193]] Reward -10482.8671014 Loss 59.9064331055
Episode 0 Step 379 Action [[ 0.3752273   0.38682179  0.39838455  0.55058785  0.48767233  0.53272249
   0.58814213  0.52850481]] Reward -10510.329163 Loss 123.815040588
Episode 0 Step 380 Action [[ 0.62047757  0.53389875  0.56607575  0.47194136  0.64515086  0.63537236
   0.46202412  0.26230451]] Reward -10543.4709765 Loss 66.8944625854
Episode 0 Step 381 Action [[ 0.44396563  0.42140364  0.35768078  0.33912213  0.74233762  0.43897315
   0.36855135  0.45080093]] Reward -10573.9041073 Loss 26.5812416077
Episode 0 Step 382 Action [[ 0.40687835  0.48273706  0.46992604  0.30313055  0.50298854  0.41844003
   0.32550334  0.39608174]] Reward -10599.6457052 Loss 46.3086776733
Episode 0 Step 383 Action [[ 0.46254641  0.41471836  0.45779622  0.44209205  0.45598923  0.54891722
   0.50179041  0.49794918]] Reward -10625.8677977 Loss 33.3779983521
Episode 0 Step 384 Action [[ 0.58452722  0.55842907  0.45799586  0.63490739  0.4443386   0.65092404
   0.33415744  0.44786677]] Reward -10654.2126389 Loss 109.973594666
Episode 0 Step 385 Action [[ 0.36529459  0.52390654  0.41700921  0.40575912  0.39708425  0.45188314
   0.47926962  0.45303868]] Reward -10679.2676018 Loss 80.8730316162
Episode 0 Step 386 Action [[ 0.59715418  0.49764185  0.56618288  0.50638082  0.44449575  0.51878972
   0.38074752  0.45530428]] Reward -10706.2242501 Loss 22.4449291229
Episode 0 Step 387 Action [[ 0.32130463  0.48057794  0.58669348  0.38822346  0.45954349  0.51292989
   0.34870558  0.42817706]] Reward -10733.6174361 Loss 166.394195557
Episode 0 Step 388 Action [[ 0.3507951   0.32211338  0.54763552  0.48742863  0.40511823  0.46414804
   0.49948594  0.37027084]] Reward -10758.2359864 Loss 151.679916382
Episode 0 Step 389 Action [[ 0.34164108  0.44553781  0.60251749  0.50315997  0.55380055  0.50263172
   0.47439315  0.64732354]] Reward -10786.8029488 Loss 24.3612995148
Episode 0 Step 390 Action [[ 0.57628353  0.5479789   0.45554429  0.50973456  0.66735037  0.24453029
   0.54457986  0.34890878]] Reward -10812.9334061 Loss 55.0519332886
Episode 0 Step 391 Action [[ 0.5810858   0.41345561  0.50981777  0.35745032  0.43735969  0.60676543
   0.60630954  0.39571629]] Reward -10841.3037631 Loss 34.6361427307
Episode 0 Step 392 Action [[ 0.3199079   0.50996926  0.55932574  0.25012976  0.48824075  0.54351805
   0.3924144   0.79347422]] Reward -10869.3010101 Loss 26.1550159454
Episode 0 Step 393 Action [[ 0.58487769  0.41382423  0.55756761  0.50709091  0.58524604  0.39214743
   0.39524768  0.49542534]] Reward -10895.0286335 Loss 25.7457809448
Episode 0 Step 394 Action [[ 0.53515573  0.29419174  0.55494515  0.72587355  0.51179707  0.33537166
   0.49188614  0.55466147]] Reward -10918.8235668 Loss 32.4286155701
Episode 0 Step 395 Action [[ 0.52164371  0.51086916  0.48509291  0.53941665  0.4073579   0.54592949
   0.43441553  0.71439741]] Reward -10946.3664802 Loss 24.1487407684
Episode 0 Step 396 Action [[ 0.51961241  0.61158488  0.35135489  0.56341646  0.26822001  0.46074405
   0.49727121  0.56888754]] Reward -10970.1018812 Loss 66.4656219482
Episode 0 Step 397 Action [[ 0.61408212  0.48613107  0.47072441  0.46064047  0.50066454  0.47170764
   0.45231324  0.52800013]] Reward -10998.1861645 Loss 141.471099854
Episode 0 Step 398 Action [[ 0.39789726  0.43928579  0.64046891  0.47111193  0.50831763  0.39841329
   0.57386708  0.54027738]] Reward -11025.18087 Loss 52.7960929871
Episode 0 Step 399 Action [[ 0.47949297  0.50285878  0.50789367  0.35264156  0.5432603   0.45509926
   0.67292942  0.49015003]] Reward -11053.3004901 Loss 77.802482605
Episode 0 Step 400 Action [[ 0.66308368  0.41800011  0.59276595  0.35577122  0.65669148  0.48674184
   0.6121915   0.3465761 ]] Reward -11083.1422561 Loss 219.835327148
Episode 0 Step 401 Action [[ 0.47580791  0.34467507  0.38500601  0.44072221  0.60390157  0.44053155
   0.46847361  0.3805679 ]] Reward -11110.005864 Loss 20.1320953369
Episode 0 Step 402 Action [[ 0.57006423  0.47764495  0.35734262  0.46012783  0.38967025  0.37916182
   0.4560616   0.4849151 ]] Reward -11132.5500244 Loss 249.387145996
Episode 0 Step 403 Action [[ 0.35137659  0.45437328  0.60437526  0.51818614  0.3017669   0.57275713
   0.54031838  0.5514447 ]] Reward -11157.707021 Loss 125.237167358
Episode 0 Step 404 Action [[ 0.46897774  0.5629439   0.52000101  0.45577268  0.47841857  0.42283193
   0.29605349  0.72905748]] Reward -11183.7443865 Loss 56.794708252
Episode 0 Step 405 Action [[ 0.43640615  0.57773702  0.37925107  0.57788409  0.5558845   0.36138297
   0.51793528  0.50498946]] Reward -11209.6630946 Loss 400.876495361
Episode 0 Step 406 Action [[ 0.4913865   0.29604722  0.43224515  0.48719505  0.52503243  0.40557422
   0.52457672  0.49175047]] Reward -11235.7333795 Loss 674.880126953
Episode 0 Step 407 Action [[ 0.4925152   0.46234544  0.64294839  0.4535576   0.51720429  0.51075261
   0.5098045   0.5321114 ]] Reward -11264.534646 Loss 47.7782669067
Episode 0 Step 408 Action [[ 0.42456959  0.53496844  0.51329321  0.5421601   0.39290383  0.57152025
   0.48201407  0.44083346]] Reward -11291.8622539 Loss 561.505493164
Episode 0 Step 409 Action [[ 0.59914026  0.44393011  0.49417068  0.4231431   0.52593568  0.38635953
   0.57217758  0.42391362]] Reward -11318.2912011 Loss 1445.17041016
Episode 0 Step 410 Action [[ 0.68782088  0.46030138  0.5026795   0.53307697  0.44507657  0.56564653
   0.54933932  0.48827766]] Reward -11346.0984286 Loss 818.812988281
Episode 0 Step 411 Action [[ 0.45760198  0.62877246  0.53619773  0.34230107  0.49478535  0.38862466
   0.38709521  0.48750882]] Reward -11372.6113171 Loss 359.818115234
Episode 0 Step 412 Action [[ 0.3723931   0.37764565  0.58828969  0.45745506  0.36387325  0.38929335
   0.45768411  0.4639213 ]] Reward -11395.5559934 Loss 2984.84716797
Episode 0 Step 413 Action [[ 0.46000326  0.37907395  0.54933729  0.46393649  0.32933261  0.40332261
   0.5150998   0.51071712]] Reward -11418.0893266 Loss 3160.25341797
Episode 0 Step 414 Action [[ 0.36344679  0.54058017  0.43425731  0.44576699  0.55131669  0.57924983
   0.66237255  0.41524653]] Reward -11447.6123377 Loss 320.829315186
Episode 0 Step 415 Action [[ 0.43565625  0.58936947  0.51435178  0.50623416  0.4645781   0.52905754
   0.57788428  0.48950762]] Reward -11475.1213976 Loss 5917.88427734
Episode 0 Step 416 Action [[ 0.45712033  0.47240562  0.4585522   0.35226459  0.48825653  0.44977545
   0.63234857  0.4836661 ]] Reward -11501.4412359 Loss 4765.24316406
Episode 0 Step 417 Action [[ 0.53722653  0.44337595  0.63645139  0.36394269  0.61414658  0.49942526
   0.46039917  0.51276576]] Reward -11530.6081038 Loss 322.269744873
Episode 0 Step 418 Action [[ 0.41855706  0.63016428  0.48453152  0.49769384  0.47661854  0.4447631
   0.37001537  0.45081234]] Reward -11556.2520034 Loss 1994.40649414
Episode 0 Step 419 Action [[ 0.48552579  0.45872637  0.55258904  0.55172964  0.42622257  0.39722555
   0.43896333  0.45340698]] Reward -11580.337975 Loss 7170.74121094
Episode 0 Step 420 Action [[ 0.59118748  0.50496797  0.66266608  0.49271613  0.40676981  0.48691153
   0.45186269  0.52418711]] Reward -11606.6517055 Loss 3107.93286133
Episode 0 Step 421 Action [[ 0.57978936  0.41588148  0.41938829  0.37767997  0.42041737  0.4749885
   0.61598813  0.34638622]] Reward -11632.119298 Loss 1219.11816406
Episode 0 Step 422 Action [[ 0.33742525  0.37519561  0.3917683   0.59709269  0.56908061  0.2937224
   0.49175712  0.50657145]] Reward -11656.3738305 Loss 4402.93847656
Episode 0 Step 423 Action [[ 0.43080306  0.4345335   0.46141206  0.5526166   0.44836926  0.48145601
   0.41014854  0.47473948]] Reward -11682.8637165 Loss 213.661972046
Episode 0 Step 424 Action [[ 0.23577293  0.42484362  0.435495    0.54630709  0.447121    0.42872897
   0.36758386  0.60243358]] Reward -11708.6550372 Loss 7760.4375
Episode 0 Step 425 Action [[ 0.26412879  0.5533236   0.47635226  0.51029207  0.3577162   0.66887179
   0.29809689  0.46690837]] Reward -11737.6608772 Loss 7019.50683594
Episode 0 Step 426 Action [[ 0.44870032  0.57930177  0.42191047  0.36358726  0.30740378  0.45689983
   0.50268222  0.55794264]] Reward -11762.0699117 Loss 340.090026855
Episode 0 Step 427 Action [[ 0.60301258  0.62772507  0.4795354   0.61620882  0.65210532  0.34389617
   0.31253454  0.37356341]] Reward -11789.945325 Loss 12897.5957031
Episode 0 Step 428 Action [[ 0.40668319  0.36350549  0.38306162  0.53560654  0.51737326  0.4606844
   0.40595638  0.49310793]] Reward -11817.2208258 Loss 16088.9941406
Episode 0 Step 429 Action [[ 0.39648463  0.51060122  0.50471404  0.4768643   0.47246944  0.56238497
   0.5213307   0.43042808]] Reward -11846.3493047 Loss 21.2499160767
Episode 0 Step 430 Action [[ 0.46703881  0.60903194  0.32189941  0.50001573  0.30387816  0.45175779
   0.43718984  0.53704179]] Reward -11870.2381524 Loss 10987.0546875
Episode 0 Step 431 Action [[ 0.55628     0.54182089  0.44907747  0.48792294  0.34653334  0.49389891
   0.44198372  0.43592071]] Reward -11895.700901 Loss 1549.84375
Episode 0 Step 432 Action [[ 0.4129707   0.51873172  0.35975766  0.52052038  0.63320578  0.33118358
   0.31397307  0.47142402]] Reward -11922.8792202 Loss 6163.29003906
Episode 0 Step 433 Action [[ 0.59327688  0.42882886  0.42243683  0.49527378  0.4039974   0.74826931
   0.49682845  0.51969023]] Reward -11953.2779174 Loss 9386.34765625
Episode 0 Step 434 Action [[ 0.48503499  0.3395165   0.4792172   0.54966402  0.57601295  0.4506904
   0.5205135   0.26978605]] Reward -11981.3830095 Loss 270.639404297
Episode 0 Step 435 Action [[ 0.60630709  0.40153707  0.52729659  0.45453632  0.46286988  0.41771985
   0.43023284  0.32750315]] Reward -12007.549746 Loss 5634.78027344
Episode 0 Step 436 Action [[ 0.58735577  0.43313677  0.4440614   0.46077889  0.43221423  0.48774931
   0.51186822  0.31415266]] Reward -12033.9292377 Loss 5311.66601562
Episode 0 Step 437 Action [[ 0.46876451  0.50298582  0.50979923  0.60932522  0.53524783  0.3948717
   0.30352184  0.52036294]] Reward -12060.7016872 Loss 527.456176758
Episode 0 Step 438 Action [[ 0.36200773  0.4174582   0.45663363  0.52415605  0.46758261  0.49927596
   0.37613539  0.29944128]] Reward -12088.2813639 Loss 4777.21972656
Episode 0 Step 439 Action [[ 0.50605956  0.48313169  0.495939    0.57300758  0.28614218  0.52414054
   0.65905319  0.44934564]] Reward -12113.5270178 Loss 173.745635986
Episode 0 Step 440 Action [[ 0.40271621  0.3795631   0.51002011  0.61158734  0.63270313  0.47287294
   0.59195385  0.55555687]] Reward -12143.7926725 Loss 3203.76196289
Episode 0 Step 441 Action [[ 0.53955581  0.37168309  0.48193496  0.59584886  0.32391217  0.49738538
   0.55583926  0.51283765]] Reward -12169.454417 Loss 1545.0559082
Episode 0 Step 442 Action [[ 0.44813801  0.52052841  0.58030557  0.51705639  0.40309853  0.48940575
   0.41129618  0.58219407]] Reward -12197.2444864 Loss 3564.07495117
Episode 0 Step 443 Action [[ 0.63252373  0.39121575  0.37058873  0.73402667  0.45109018  0.43662553
   0.42932511  0.61286325]] Reward -12223.6901572 Loss 5718.74804688
Episode 0 Step 444 Action [[ 0.42292327  0.64618265  0.55271332  0.47361698  0.36898633  0.40359534
   0.5271315   0.37795983]] Reward -12250.3517 Loss 4677.6953125
Episode 0 Step 445 Action [[ 0.39954949  0.42201378  0.4446667   0.41176291  0.50678333  0.46778219
   0.29588344  0.56548834]] Reward -12278.8013967 Loss 20481.0976562
Episode 0 Step 446 Action [[ 0.49241431  0.46130741  0.49958251  0.57693896  0.42216029  0.63746012
   0.56997489  0.52776255]] Reward -12308.2213035 Loss 2860.17626953
Episode 0 Step 447 Action [[ 0.45428191  0.56038857  0.50081324  0.44408873  0.58267972  0.4606324
   0.45896275  0.46913812]] Reward -12337.9137519 Loss 21064.5390625
Episode 0 Step 448 Action [[ 0.55429923  0.42553636  0.48227563  0.540793    0.41285435  0.44897752
   0.56392498  0.45442031]] Reward -12363.5919211 Loss 32006.7988281
Episode 0 Step 449 Action [[ 0.56417631  0.58202149  0.39179791  0.54158058  0.43166844  0.49786649
   0.57404457  0.41697057]] Reward -12390.7700709 Loss 350.003845215
Episode 0 Step 450 Action [[ 0.42744693  0.45794772  0.55503273  0.50908709  0.52393707  0.43363599
   0.44833973  0.45603791]] Reward -12418.657115 Loss 10818.6748047
Episode 0 Step 451 Action [[ 0.47819752  0.30737774  0.52954509  0.56239881  0.38044911  0.42004896
   0.50613327  0.49299428]] Reward -12443.2646922 Loss 4831.92578125
Episode 0 Step 452 Action [[ 0.31248303  0.48665201  0.44308238  0.41436579  0.56268941  0.30475664
   0.51431617  0.56662957]] Reward -12469.5123454 Loss 15852.9003906
Episode 0 Step 453 Action [[ 0.4933673   0.55899723  0.49723424  0.45287969  0.33489631  0.44493801
   0.4279032   0.41079204]] Reward -12493.9951342 Loss 715.91229248
Episode 0 Step 454 Action [[ 0.48735362  0.48638162  0.36965434  0.39674467  0.31539955  0.5285892
   0.42071249  0.43545067]] Reward -12518.7776278 Loss 7990.02978516
Episode 0 Step 455 Action [[ 0.4224699   0.46910843  0.33078886  0.32985115  0.4404592   0.55015834
   0.52217385  0.57459331]] Reward -12545.4873401 Loss 102.663650513
Episode 0 Step 456 Action [[ 0.49294367  0.42494135  0.51258448  0.4920786   0.30950244  0.46916953
   0.60719008  0.38054956]] Reward -12568.3074459 Loss 10471.5498047
Episode 0 Step 457 Action [[ 0.37328163  0.32429661  0.60794336  0.51383686  0.59868329  0.48850005
   0.60802418  0.69122131]] Reward -12596.7657954 Loss 881.436584473
Episode 0 Step 458 Action [[ 0.46682264  0.76980055  0.32106487  0.4858374   0.43628564  0.4868347
   0.57903388  0.59397257]] Reward -12623.2054183 Loss 5664.6171875
Episode 0 Step 459 Action [[ 0.42311176  0.39531527  0.51365722  0.39079651  0.49414485  0.58367547
   0.5192763   0.45681887]] Reward -12651.8573993 Loss 6446.56201172
Episode 0 Step 460 Action [[ 0.3251444   0.56029671  0.43930672  0.61252911  0.62269963  0.5604229
   0.38922328  0.32045401]] Reward -12682.1878731 Loss 190.663818359
Episode 0 Step 461 Action [[ 0.60468664  0.42834547  0.43477929  0.65996696  0.50597947  0.53211573
   0.44476526  0.5045903 ]] Reward -12710.4839613 Loss 4281.62792969
Episode 0 Step 462 Action [[ 0.54274027  0.62905945  0.42551655  0.31952695  0.35065103  0.6110626
   0.5348608   0.3477379 ]] Reward -12738.8481521 Loss 72.0057601929
Episode 0 Step 463 Action [[ 0.39729915  0.47413594  0.31498303  0.48176184  0.32734467  0.5285981
   0.37807214  0.48558301]] Reward -12763.5313466 Loss 3224.18896484
Episode 0 Step 464 Action [[ 0.60720722  0.48101757  0.41851492  0.50253944  0.4642378   0.2870956
   0.50810794  0.34748853]] Reward -12786.7631616 Loss 586.369140625
Episode 0 Step 465 Action [[ 0.60537374  0.52981839  0.51404169  0.64476689  0.41077169  0.48272897
   0.45983576  0.31633454]] Reward -12812.9505407 Loss 1629.61376953
Episode 0 Step 466 Action [[ 0.47847825  0.41571578  0.52895214  0.38559387  0.51438091  0.49791417
   0.66744752  0.22727582]] Reward -12841.6789532 Loss 1490.5690918
Episode 0 Step 467 Action [[ 0.38894197  0.34859256  0.55969054  0.33715568  0.48385148  0.51547055
   0.66916726  0.44999155]] Reward -12869.3644437 Loss 499.847717285
Episode 0 Step 468 Action [[ 0.66005078  0.47387086  0.48897043  0.58784731  0.43770024  0.4920527
   0.73099154  0.3706037 ]] Reward -12895.2316514 Loss 1352.15344238
Episode 0 Step 469 Action [[ 0.35613615  0.55948146  0.42831071  0.45913338  0.26387958  0.4506626
   0.43832008  0.31407321]] Reward -12918.2188855 Loss 1153.92150879
Episode 0 Step 470 Action [[ 0.53496506  0.42108432  0.43640057  0.26678802  0.45549238  0.52183776
   0.42777829  0.62175402]] Reward -12945.1829781 Loss 1653.75610352
Episode 0 Step 471 Action [[ 0.57421072  0.54822485  0.3657589   0.43182181  0.63529981  0.33359103
   0.36204291  0.28247978]] Reward -12971.087036 Loss 513.515869141
Episode 0 Step 472 Action [[ 0.44590059  0.41801628  0.50457895  0.49620028  0.64017395  0.42312064
   0.50951976  0.50590893]] Reward -12998.7446815 Loss 2867.68505859
Episode 0 Step 473 Action [[ 0.42583526  0.59597095  0.4950939   0.5147688   0.43739173  0.37617205
   0.63818411  0.37456251]] Reward -13022.9851144 Loss 139.282791138
Episode 0 Step 474 Action [[ 0.49083763  0.55021637  0.5290999   0.34518027  0.64094775  0.39266037
   0.66008891  0.50281773]] Reward -13051.2978628 Loss 1626.62902832
Episode 0 Step 475 Action [[ 0.63306075  0.50825823  0.34288162  0.43905376  0.47092656  0.51453664
   0.55126402  0.46410593]] Reward -13077.5178571 Loss 93.6241760254
Episode 0 Step 476 Action [[ 0.50449215  0.4491869   0.49710024  0.36819502  0.38162573  0.5875042
   0.51231755  0.57483405]] Reward -13103.8133482 Loss 1278.57666016
Episode 0 Step 477 Action [[ 0.32216807  0.59560562  0.43174377  0.62189131  0.47694635  0.46851641
   0.42722384  0.62798581]] Reward -13129.6212603 Loss 537.044555664
Episode 0 Step 478 Action [[ 0.53441135  0.30798245  0.41497165  0.53414994  0.58492262  0.59606997
   0.41147654  0.58347154]] Reward -13159.5808688 Loss 418.373596191
Episode 0 Step 479 Action [[ 0.364572    0.23379308  0.35764268  0.51311111  0.60031183  0.60101443
   0.48101408  0.48159636]] Reward -13189.8362446 Loss 1195.8963623
Episode 0 Step 480 Action [[ 0.48338005  0.45252735  0.46204783  0.49243238  0.24591736  0.37252342
   0.36282232  0.4939715 ]] Reward -13211.176056 Loss 200.532424927
Episode 0 Step 481 Action [[ 0.28774665  0.33345475  0.48152192  0.60694797  0.36034534  0.41884942
   0.50400842  0.40779984]] Reward -13234.9494384 Loss 2194.96582031
Episode 0 Step 482 Action [[ 0.51033612  0.46696564  0.45030042  0.41683424  0.47475547  0.53125155
   0.43169445  0.34491249]] Reward -13263.414048 Loss 695.896911621
Episode 0 Step 483 Action [[ 0.30415233  0.27349378  0.5409068   0.30156664  0.5553217   0.35084115
   0.52795981  0.47551009]] Reward -13289.3555554 Loss 755.30645752
Episode 0 Step 484 Action [[ 0.59648147  0.5362277   0.24763502  0.44799961  0.3967424   0.39828223
   0.54054179  0.37637155]] Reward -13312.3097472 Loss 1542.89685059
Episode 0 Step 485 Action [[ 0.39294411  0.54115758  0.42774202  0.64106376  0.56989886  0.54282994
   0.53431993  0.40239432]] Reward -13341.2858352 Loss 412.001434326
Episode 0 Step 486 Action [[ 0.45402572  0.60508154  0.35468257  0.53854694  0.45938324  0.35963146
   0.46451746  0.54930057]] Reward -13366.2095025 Loss 3340.29052734
Episode 0 Step 487 Action [[ 0.401236    0.41785663  0.44349544  0.30755297  0.44844113  0.46771533
   0.42904864  0.35991285]] Reward -13392.6834878 Loss 1201.3347168
Episode 0 Step 488 Action [[ 0.47606825  0.48289852  0.42345518  0.49606071  0.36555976  0.4811861
   0.44711562  0.33773334]] Reward -13417.0953913 Loss 1314.75244141
Episode 0 Step 489 Action [[ 0.49118996  0.31714173  0.40307077  0.51563686  0.39748778  0.35746166
   0.53451923  0.44219144]] Reward -13439.6397144 Loss 1765.53527832
Episode 0 Step 490 Action [[ 0.39920294  0.40673079  0.41343946  0.52302872  0.37683348  0.48314546
   0.45517858  0.49314802]] Reward -13464.5172719 Loss 79.0027008057
Episode 0 Step 491 Action [[ 0.3061769   0.48419113  0.43595891  0.27278401  0.5456745   0.47418294
   0.34921443  0.51930444]] Reward -13492.6234763 Loss 1230.32885742
Episode 0 Step 492 Action [[ 0.42814035  0.36817962  0.50518973  0.32090615  0.64201057  0.57203841
   0.51917555  0.45045068]] Reward -13522.8050721 Loss 66.7265625
Episode 0 Step 493 Action [[ 0.5776194   0.35569542  0.50651928  0.52636329  0.37262003  0.47300372
   0.63001565  0.43052782]] Reward -13546.1374509 Loss 1145.43554688
Episode 0 Step 494 Action [[ 0.63426468  0.45267721  0.60884371  0.37001643  0.38863648  0.38962069
   0.55897511  0.48456803]] Reward -13569.5384269 Loss 1292.91235352
Episode 0 Step 495 Action [[ 0.4028391   0.38247167  0.40713256  0.41265333  0.44160121  0.48629907
   0.55854015  0.47499027]] Reward -13594.3912184 Loss 139.682952881
Episode 0 Step 496 Action [[ 0.34262421  0.4344588   0.68059766  0.53182248  0.30843707  0.49633572
   0.46286567  0.3589224 ]] Reward -13618.0632384 Loss 2272.42504883
Episode 0 Step 497 Action [[ 0.4272693   0.51572256  0.55800255  0.73717533  0.54188299  0.51391772
   0.61844359  0.32895668]] Reward -13646.4745882 Loss 714.415649414
Episode 0 Step 498 Action [[ 0.57499871  0.34511608  0.61919275  0.35462928  0.51894683  0.38335436
   0.60616686  0.51847703]] Reward -13673.3965945 Loss 379.735443115
Episode 0 Step 499 Action [[ 0.58522936  0.36683132  0.3911952   0.45301855  0.36490518  0.50793019
   0.56313109  0.52192412]] Reward -13698.3314466 Loss 1383.08129883
Episode 0 Step 500 Action [[ 0.35312913  0.48909343  0.39658937  0.51717094  0.51132162  0.70353863
   0.5183892   0.48493136]] Reward -13729.3391451 Loss 433.613586426
Episode 0 Step 501 Action [[ 0.30891802  0.42175937  0.51600063  0.38943237  0.50343847  0.44972235
   0.39498828  0.46454718]] Reward -13756.2426106 Loss 2107.19262695
Episode 0 Step 502 Action [[ 0.56741392  0.69024657  0.4991894   0.54756197  0.42223399  0.34365234
   0.45621493  0.50602068]] Reward -13780.1891656 Loss 261.895568848
Episode 0 Step 503 Action [[ 0.5516028   0.67184723  0.5098514   0.41226044  0.36228937  0.27709001
   0.50105578  0.48436687]] Reward -13802.4006851 Loss 4135.34960938
Episode 0 Step 504 Action [[ 0.56924892  0.52951334  0.4609625   0.4764915   0.3117555   0.48420703
   0.46194378  0.41398031]] Reward -13826.3646523 Loss 1567.63500977
Episode 0 Step 505 Action [[ 0.45887981  0.52146825  0.47536378  0.4667385   0.42439975  0.52445511
   0.53629613  0.4681728 ]] Reward -13853.0511361 Loss 448.376342773
Episode 0 Step 506 Action [[ 0.53436029  0.55029387  0.35039492  0.45162478  0.45033099  0.42411126
   0.57889883  0.39826166]] Reward -13878.174239 Loss 1961.9017334
Episode 0 Step 507 Action [[ 0.43906499  0.53664148  0.41295538  0.5834229   0.53077284  0.32452145
   0.62285416  0.56596078]] Reward -13903.0613935 Loss 410.529388428
Episode 0 Step 508 Action [[ 0.48915079  0.6106172   0.76163566  0.40838667  0.42720626  0.40688741
   0.59804938  0.38358582]] Reward -13929.3892487 Loss 519.764221191
Episode 0 Step 509 Action [[ 0.48417336  0.57260479  0.40456972  0.38238492  0.3194436   0.34287631
   0.48291222  0.64865532]] Reward -13951.1849883 Loss 924.682434082
Episode 0 Step 510 Action [[ 0.41751579  0.38220023  0.58059019  0.57349114  0.45962292  0.41869284
   0.48882534  0.43226447]] Reward -13976.1885181 Loss 120.565231323
Episode 0 Step 511 Action [[ 0.49432701  0.4341505   0.51260951  0.55545025  0.6277906   0.4209016
   0.60236627  0.39896155]] Reward -14004.6984038 Loss 1621.87841797
Episode 0 Step 512 Action [[ 0.60236793  0.47853971  0.49270821  0.45421631  0.27787226  0.46988644
   0.51585644  0.44734619]] Reward -14028.501759 Loss 1014.1763916
Episode 0 Step 513 Action [[ 0.52080331  0.46328368  0.54191808  0.51860844  0.40933364  0.49624446
   0.49256675  0.56542682]] Reward -14054.8604186 Loss 781.81262207
Episode 0 Step 514 Action [[ 0.38924954  0.45187189  0.55885096  0.56413351  0.44188855  0.47424293
   0.38919108  0.45269358]] Reward -14081.5455117 Loss 2283.58837891
Episode 0 Step 515 Action [[ 0.65544278  0.5053199   0.42580124  0.52504061  0.60759935  0.62085983
   0.60978315  0.40199283]] Reward -14113.6572267 Loss 151.979125977
Episode 0 Step 516 Action [[ 0.40312747  0.53900156  0.30852081  0.47669773  0.42905642  0.51307294
   0.33673377  0.55010179]] Reward -14140.6944958 Loss 1020.71563721
Episode 0 Step 517 Action [[ 0.72039896  0.63867899  0.48891361  0.50974814  0.46408769  0.53697489
   0.50699091  0.44743687]] Reward -14169.3203639 Loss 681.406066895
Episode 0 Step 518 Action [[ 0.47860672  0.36670633  0.53043177  0.42209917  0.37285581  0.43369255
   0.32180933  0.47709892]] Reward -14193.9756726 Loss 78.011932373
Episode 0 Step 519 Action [[ 0.47587854  0.23124761  0.51998483  0.56978441  0.53410845  0.33661641
   0.51724322  0.29919242]] Reward -14218.8840817 Loss 1286.72399902
Episode 0 Step 520 Action [[ 0.35961856  0.53867165  0.57418975  0.4856159   0.44523658  0.43601218
   0.55287687  0.26197425]] Reward -14245.4610764 Loss 1986.81567383
Episode 0 Step 521 Action [[ 0.34955146  0.55481328  0.35828155  0.54384003  0.44640103  0.60209232
   0.50501006  0.52133914]] Reward -14274.1898601 Loss 596.417480469
Episode 0 Step 522 Action [[ 0.50847727  0.52750288  0.54803567  0.41650792  0.52763137  0.63180117
   0.38637189  0.52376036]] Reward -14305.478683 Loss 1103.61914062
Episode 0 Step 523 Action [[ 0.64284847  0.50335752  0.628388    0.56231261  0.57665015  0.47675246
   0.50599241  0.41920454]] Reward -14334.6376912 Loss 2983.24804688
Episode 0 Step 524 Action [[ 0.4157088   0.55320903  0.41737502  0.50537324  0.42283147  0.60397062
   0.41159743  0.5412069 ]] Reward -14363.2741284 Loss 1889.04882812
Episode 0 Step 525 Action [[ 0.38602416  0.53097567  0.65836146  0.47058431  0.36722597  0.47063668
   0.52277806  0.48959392]] Reward -14389.3111634 Loss 491.590148926
Episode 0 Step 526 Action [[ 0.43972054  0.51909303  0.34247876  0.48646052  0.61774518  0.43477236
   0.3088513   0.49964334]] Reward -14417.8416025 Loss 3957.00317383
Episode 0 Step 527 Action [[ 0.51559276  0.62482096  0.41516219  0.26698364  0.53777161  0.47056254
   0.50958001  0.54500831]] Reward -14446.1265136 Loss 1475.73449707
Episode 0 Step 528 Action [[ 0.40601855  0.20801511  0.40548271  0.50696854  0.46064887  0.38535886
   0.53974496  0.47610171]] Reward -14469.2679729 Loss 405.465270996
Episode 0 Step 529 Action [[ 0.43827152  0.5576879   0.33863998  0.33413252  0.68585755  0.43077242
   0.38480679  0.53048486]] Reward -14498.2412379 Loss 1395.3059082
Episode 0 Step 530 Action [[ 0.54054437  0.41407598  0.55904261  0.50391312  0.58324867  0.48809063
   0.48179305  0.46956762]] Reward -14526.0816054 Loss 224.114761353
Episode 0 Step 531 Action [[ 0.51843568  0.44167276  0.49133073  0.28319709  0.25815813  0.67957461
   0.51017284  0.42333094]] Reward -14551.9572456 Loss 558.350524902
Episode 0 Step 532 Action [[ 0.44272355  0.56020673  0.44902784  0.35670681  0.57661407  0.55105763
   0.33815437  0.41910819]] Reward -14580.4995036 Loss 1162.93432617
Episode 0 Step 533 Action [[ 0.54573671  0.56374987  0.35590428  0.43316802  0.49678624  0.58005244
   0.36664643  0.51361144]] Reward -14607.7248819 Loss 426.15826416
Episode 0 Step 534 Action [[ 0.45646299  0.63021252  0.52034475  0.38699072  0.67682781  0.29956706
   0.56455587  0.47713271]] Reward -14634.1641962 Loss 34.6713294983
Episode 0 Step 535 Action [[ 0.28900469  0.4402818   0.69138759  0.58221777  0.41286177  0.47946514
   0.55452899  0.41066119]] Reward -14659.0422263 Loss 291.172393799
Episode 0 Step 536 Action [[ 0.592231    0.51153184  0.3597781   0.58956996  0.43372999  0.40968229
   0.30291566  0.55880483]] Reward -14683.2391632 Loss 81.8281478882
Episode 0 Step 537 Action [[ 0.59264325  0.48777948  0.40484275  0.47653086  0.3498135   0.49565441
   0.49881922  0.45953209]] Reward -14708.2672324 Loss 221.743148804
Episode 0 Step 538 Action [[ 0.61476912  0.69298892  0.55404912  0.60876369  0.4728566   0.41767399
   0.50487698  0.49718603]] Reward -14735.0148982 Loss 516.830566406
Episode 0 Step 539 Action [[ 0.52212367  0.59899603  0.42104991  0.50540141  0.47037208  0.3964012
   0.44366143  0.62632607]] Reward -14761.3014505 Loss 229.998031616
Episode 0 Step 540 Action [[ 0.40917343  0.48848496  0.3826943   0.57043966  0.4944353   0.65901867
   0.36800406  0.50385158]] Reward -14791.9608381 Loss 123.124259949
Episode 0 Step 541 Action [[ 0.65672695  0.29088388  0.42707287  0.59914663  0.41291248  0.44224086
   0.63612698  0.20037329]] Reward -14817.3604747 Loss 416.605316162
Episode 0 Step 542 Action [[ 0.45664294  0.44385693  0.48524144  0.57045147  0.51695059  0.38417159
   0.35223819  0.3413087 ]] Reward -14844.491457 Loss 141.006774902
Episode 0 Step 543 Action [[ 0.47047537  0.66143575  0.45040961  0.59559051  0.40624424  0.50248474
   0.61282915  0.44237386]] Reward -14872.3834002 Loss 23.0240306854
Episode 0 Step 544 Action [[ 0.38702888  0.62876698  0.43669133  0.38797802  0.48147722  0.43833351
   0.54238184  0.48457815]] Reward -14900.4994803 Loss 135.024856567
Episode 0 Step 545 Action [[ 0.45689874  0.61866165  0.48375797  0.56021493  0.34440707  0.50105212
   0.50984727  0.3979685 ]] Reward -14926.5406225 Loss 132.282608032
Episode 0 Step 546 Action [[ 0.48489856  0.33276556  0.6659969   0.41726083  0.41348658  0.53281299
   0.35549343  0.37604588]] Reward -14954.2197335 Loss 22.7208347321
Episode 0 Step 547 Action [[ 0.52362179  0.51806279  0.44056949  0.47937227  0.51889282  0.55497491
   0.41069359  0.56778054]] Reward -14983.4272462 Loss 227.285491943
Episode 0 Step 548 Action [[ 0.62392139  0.45776886  0.39503668  0.48336416  0.4446475   0.49985927
   0.49197272  0.4258865 ]] Reward -15010.0272382 Loss 408.475189209
Episode 0 Step 549 Action [[ 0.37691399  0.42796391  0.6414793   0.299611    0.43093683  0.41353372
   0.37784918  0.56973651]] Reward -15035.5240419 Loss 30.899433136
Episode 0 Step 550 Action [[ 0.30687378  0.4872505   0.39057355  0.45774627  0.36069484  0.59234827
   0.60340792  0.31036357]] Reward -15061.3541121 Loss 368.593322754
Episode 0 Step 551 Action [[ 0.4904502   0.47426108  0.5764598   0.49119969  0.56259762  0.49592378
   0.54993798  0.43184115]] Reward -15089.6112769 Loss 827.050109863
Episode 0 Step 552 Action [[ 0.50776     0.55823686  0.44447465  0.45751766  0.49640741  0.55670413
   0.59178916  0.48643683]] Reward -15117.8905927 Loss 52.81016922
Episode 0 Step 553 Action [[ 0.48349483  0.56285271  0.39894304  0.46946539  0.6359928   0.51326812
   0.46165382  0.50202217]] Reward -15147.6958545 Loss 532.127624512
Episode 0 Step 554 Action [[ 0.4872267   0.38604015  0.45179362  0.29778066  0.54169058  0.64226716
   0.29894802  0.34907076]] Reward -15177.793924 Loss 1391.58081055
Episode 0 Step 555 Action [[ 0.36178137  0.42903466  0.47449446  0.44172421  0.37027745  0.40767457
   0.35186887  0.53371598]] Reward -15200.3777368 Loss 384.283081055
Episode 0 Step 556 Action [[ 0.37360722  0.43615544  0.24042518  0.3434513   0.44208914  0.39814553
   0.51066953  0.47326529]] Reward -15223.5015225 Loss 37.4275169373
Episode 0 Step 557 Action [[ 0.4856261   0.47652916  0.49150075  0.55160153  0.4303085   0.47872867
   0.42251605  0.36399001]] Reward -15248.2441862 Loss 397.227294922
Episode 0 Step 558 Action [[ 0.48004773  0.64920101  0.61199251  0.6428091   0.24045843  0.39598941
   0.43474524  0.55259744]] Reward -15269.9629539 Loss 60.6158447266
Episode 0 Step 559 Action [[ 0.39565313  0.48601347  0.39484896  0.41514176  0.34834828  0.46466359
   0.35417999  0.59287428]] Reward -15294.5667893 Loss 146.370788574
Episode 0 Step 560 Action [[ 0.45444885  0.29820346  0.40119167  0.51955821  0.37680141  0.41679031
   0.52969795  0.69028497]] Reward -15317.9156647 Loss 253.413299561
Episode 0 Step 561 Action [[ 0.4280344   0.53136145  0.60278312  0.40515136  0.38454821  0.25810978
   0.47492679  0.56947421]] Reward -15340.1477108 Loss 87.3332672119
Episode 0 Step 562 Action [[ 0.57168752  0.39831493  0.50560946  0.47272537  0.38430578  0.64906555
   0.38780027  0.54819064]] Reward -15367.9395074 Loss 52.0040092468
Episode 0 Step 563 Action [[ 0.49403143  0.35902338  0.57186438  0.5212244   0.51464722  0.6211638
   0.54825868  0.54181769]] Reward -15397.6306354 Loss 298.303039551
Episode 0 Step 564 Action [[ 0.31428585  0.52084954  0.43652659  0.50983091  0.52953401  0.52381226
   0.5335769   0.36557485]] Reward -15426.2516042 Loss 617.475708008
Episode 0 Step 565 Action [[ 0.50280344  0.4688055   0.41782198  0.41733486  0.51222314  0.4445319
   0.49474113  0.33637975]] Reward -15453.1422409 Loss 266.260437012
Episode 0 Step 566 Action [[ 0.47655678  0.44056017  0.54555924  0.41973435  0.42922876  0.54962976
   0.31578536  0.54415747]] Reward -15480.34603 Loss 304.326049805
Episode 0 Step 567 Action [[ 0.47638996  0.49754515  0.54564313  0.65283261  0.37280471  0.41873751
   0.59322412  0.6559816 ]] Reward -15504.2874071 Loss 1709.38549805
Episode 0 Step 568 Action [[ 0.50243827  0.47032057  0.44530208  0.52190169  0.44449651  0.53648783
   0.57868601  0.34568842]] Reward -15532.0438892 Loss 1271.87561035
Episode 0 Step 569 Action [[ 0.42146596  0.32134335  0.56896215  0.51603607  0.50450287  0.36929859
   0.41288874  0.52163467]] Reward -15557.9693285 Loss 339.956939697
Episode 0 Step 570 Action [[ 0.41168432  0.519658    0.65179988  0.44759951  0.66628285  0.36976277
   0.33219974  0.39461303]] Reward -15587.4675528 Loss 5062.20458984
Episode 0 Step 571 Action [[ 0.52747803  0.6640491   0.47289792  0.49431922  0.4757112   0.35310526
   0.58231941  0.48069346]] Reward -15612.9960151 Loss 16158.8925781
Episode 0 Step 572 Action [[ 0.40831391  0.44485086  0.37043954  0.37228648  0.57240332  0.40779415
   0.50915387  0.51247826]] Reward -15640.1660821 Loss 8635.69921875
Episode 0 Step 573 Action [[ 0.5723466   0.46478954  0.58323996  0.41043332  0.36162537  0.56466211
   0.60947862  0.72377555]] Reward -15666.4967043 Loss 895.79119873
Episode 0 Step 574 Action [[ 0.34686899  0.56232803  0.52335059  0.53758552  0.5683506   0.50587172
   0.52314189  0.55925755]] Reward -15695.1968136 Loss 2295.07617188
Episode 0 Step 575 Action [[ 0.4640982   0.56060556  0.63532922  0.48543492  0.62394319  0.46462131
   0.50687758  0.4416616 ]] Reward -15724.9090547 Loss 6210.86132812
Episode 0 Step 576 Action [[ 0.31050803  0.49449761  0.58443845  0.5887142   0.62159877  0.58348254
   0.40685968  0.52088913]] Reward -15756.3500033 Loss 2795.93994141
Episode 0 Step 577 Action [[ 0.4181541   0.56681121  0.53970461  0.57164933  0.3391749   0.51832658
   0.57091886  0.60562659]] Reward -15782.5121891 Loss 74.559753418
Episode 0 Step 578 Action [[ 0.45767599  0.44734009  0.57597635  0.71337532  0.37468067  0.281382
   0.40657629  0.47667954]] Reward -15805.2858364 Loss 1015.75134277
Episode 0 Step 579 Action [[ 0.47968509  0.4730529   0.39384495  0.56422828  0.40708903  0.36125964
   0.43596268  0.43322348]] Reward -15830.4684979 Loss 2104.01708984
Episode 0 Step 580 Action [[ 0.47161733  0.47522088  0.31413225  0.41021748  0.44165641  0.54989036
   0.4512002   0.41826849]] Reward -15859.1533924 Loss 2382.11425781
Episode 0 Step 581 Action [[ 0.51292993  0.58012458  0.55658347  0.47095086  0.58508194  0.553346
   0.46395066  0.4672928 ]] Reward -15890.5216224 Loss 1665.72705078
Episode 0 Step 582 Action [[ 0.46819114  0.39892571  0.4340215   0.45587658  0.4266168   0.46448131
   0.55277539  0.50653076]] Reward -15916.5034924 Loss 38.734046936
Episode 0 Step 583 Action [[ 0.56460275  0.71620624  0.40406148  0.40179175  0.40768708  0.42113505
   0.35704703  0.43184394]] Reward -15941.9624149 Loss 1263.40942383
Episode 0 Step 584 Action [[ 0.34451041  0.50931686  0.42917135  0.35286899  0.43027823  0.66690352
   0.35392544  0.54063834]] Reward -15971.0235866 Loss 2944.25488281
Episode 0 Step 585 Action [[ 0.54702308  0.42784159  0.5644857   0.38018846  0.36530896  0.63163427
   0.46098843  0.51832794]] Reward -15997.9493163 Loss 771.280761719
Episode 0 Step 586 Action [[ 0.48200037  0.40498068  0.49680878  0.41029699  0.39168919  0.55161324
   0.40879794  0.63132795]] Reward -16023.4380559 Loss 26.9113044739
Episode 0 Step 587 Action [[ 0.42848915  0.51730778  0.55556305  0.23724709  0.3245274   0.58089247
   0.32966188  0.5313411 ]] Reward -16048.7251402 Loss 546.698486328
Episode 0 Step 588 Action [[ 0.41688052  0.58968633  0.65173814  0.56126992  0.46966267  0.37079776
   0.43820197  0.47674371]] Reward -16072.5039064 Loss 1858.92602539
Episode 0 Step 589 Action [[ 0.35600114  0.39396686  0.48662541  0.56254268  0.31912777  0.45053257
   0.39313117  0.49774682]] Reward -16095.0035538 Loss 3076.89746094
Episode 0 Step 590 Action [[ 0.48872495  0.39894299  0.4503819   0.46305665  0.4742474   0.4718649
   0.45417642  0.23117227]] Reward -16121.1294429 Loss 1912.30981445
Episode 0 Step 591 Action [[ 0.55874716  0.32217246  0.52698318  0.34294506  0.46185209  0.48385979
   0.64711346  0.73514929]] Reward -16147.2980106 Loss 59.6372909546
Episode 0 Step 592 Action [[ 0.55079242  0.46259157  0.4554054   0.53640288  0.62014752  0.55983582
   0.40696898  0.66791155]] Reward -16177.0179295 Loss 2910.85327148
Episode 0 Step 593 Action [[ 0.45111705  0.44462168  0.53832075  0.39421814  0.51127932  0.39860209
   0.51259834  0.49370838]] Reward -16202.874944 Loss 5519.54345703
Episode 0 Step 594 Action [[ 0.53213539  0.44632744  0.4598569   0.50027605  0.30554634  0.51558551
   0.41021992  0.5236211 ]] Reward -16226.6585358 Loss 2205.27392578
Episode 0 Step 595 Action [[ 0.41229674  0.53453424  0.45753088  0.38479453  0.47202192  0.4002599
   0.33405851  0.41407776]] Reward -16251.8651057 Loss 563.285644531
Episode 0 Step 596 Action [[ 0.50540194  0.41615377  0.3272308   0.51782004  0.43867353  0.54972622
   0.41744223  0.49158982]] Reward -16277.9745723 Loss 140.890457153
Episode 0 Step 597 Action [[ 0.50435335  0.47955863  0.28020474  0.54977857  0.48473891  0.35287187
   0.39035309  0.42552299]] Reward -16301.9666854 Loss 1760.91320801
Episode 0 Step 598 Action [[ 0.59939775  0.54221969  0.62586292  0.3336783   0.45447591  0.5552662
   0.54253522  0.71077021]] Reward -16330.540483 Loss 3484.93920898
Episode 0 Step 599 Action [[ 0.4913336   0.46731837  0.4788916   0.38187249  0.45953951  0.47122616
   0.51553607  0.55262114]] Reward -16356.3292761 Loss 1321.86767578
Episode 0 Step 600 Action [[ 0.5440376   0.50411433  0.41600991  0.44058764  0.3604369   0.38428651
   0.43714878  0.47596316]] Reward -16378.572916 Loss 450.144042969
Episode 0 Step 601 Action [[ 0.63947897  0.50172168  0.49485099  0.43586766  0.46640938  0.37967858
   0.26032051  0.55036099]] Reward -16402.8475101 Loss 29.7889881134
Episode 0 Step 602 Action [[ 0.70492465  0.54393055  0.37780647  0.48051357  0.60794185  0.50704602
   0.45021645  0.40137614]] Reward -16431.5337849 Loss 201.47177124
Episode 0 Step 603 Action [[ 0.45763687  0.635863    0.4723386   0.53813019  0.3780448   0.51545009
   0.36725642  0.55618481]] Reward -16457.2441153 Loss 242.382995605
Episode 0 Step 604 Action [[ 0.41148357  0.48295783  0.525361    0.55165208  0.48637573  0.30554594
   0.38235648  0.51314153]] Reward -16481.3757602 Loss 151.371673584
Episode 0 Step 605 Action [[ 0.46206072  0.54513761  0.49799825  0.5044551   0.3250092   0.42668368
   0.40727961  0.50349319]] Reward -16505.3200143 Loss 40.2953872681
Episode 0 Step 606 Action [[ 0.469877    0.49496251  0.46437895  0.36766534  0.39436975  0.51313955
   0.52132512  0.41188994]] Reward -16531.720423 Loss 52.0712127686
Episode 0 Step 607 Action [[ 0.42603628  0.42098775  0.63270697  0.45250063  0.45571496  0.54474012
   0.4188107   0.60112925]] Reward -16559.3407091 Loss 230.77355957
Episode 0 Step 608 Action [[ 0.64306601  0.68725864  0.44145514  0.39408472  0.35759508  0.438631
   0.44695581  0.50287693]] Reward -16583.6331742 Loss 583.118774414
Episode 0 Step 609 Action [[ 0.43232895  0.45440802  0.5552939   0.52489471  0.50768071  0.4022856
   0.34847263  0.63006917]] Reward -16609.2217328 Loss 574.889892578
Episode 0 Step 610 Action [[ 0.37910625  0.52436482  0.46644396  0.52344398  0.57604381  0.64473206
   0.44818147  0.49869819]] Reward -16640.4802683 Loss 249.508422852
Episode 0 Step 611 Action [[ 0.41694109  0.33587733  0.33360716  0.48010015  0.45768548  0.42610207
   0.53265747  0.60858998]] Reward -16665.3715626 Loss 68.4172363281
Episode 0 Step 612 Action [[ 0.51631708  0.35528633  0.46432644  0.45883078  0.44929044  0.23565355
   0.60734336  0.41751613]] Reward -16687.288535 Loss 40.7916145325
Episode 0 Step 613 Action [[ 0.57792263  0.42742635  0.41231178  0.44497873  0.54407175  0.46517773
   0.67751867  0.66815718]] Reward -16714.7040718 Loss 121.282402039
Episode 0 Step 614 Action [[ 0.55219495  0.47444288  0.50911946  0.62977477  0.40244459  0.47846893
   0.5135799   0.49584677]] Reward -16740.166571 Loss 51.9809494019
Episode 0 Step 615 Action [[ 0.31483424  0.50051882  0.50352967  0.35987274  0.64767995  0.51073746
   0.38035607  0.59140969]] Reward -16771.2562904 Loss 27.2929954529
Episode 0 Step 616 Action [[ 0.53477114  0.43452566  0.62327662  0.55770691  0.47673785  0.54781277
   0.51026609  0.4927686 ]] Reward -16799.4342403 Loss 119.632774353
Episode 0 Step 617 Action [[ 0.65813405  0.49686846  0.58649935  0.41366777  0.52165186  0.58515461
   0.61141839  0.65704536]] Reward -16829.5483048 Loss 405.390716553
Episode 0 Step 618 Action [[ 0.30315025  0.50361307  0.52166743  0.44726604  0.55268898  0.48264066
   0.5032303   0.61156953]] Reward -16857.8693909 Loss 1726.82788086
Episode 0 Step 619 Action [[ 0.39644909  0.43652971  0.47675834  0.4172624   0.40090719  0.45482806
   0.60713817  0.49720153]] Reward -16882.6708672 Loss 5372.89013672
Episode 0 Step 620 Action [[ 0.27447533  0.35582558  0.51270299  0.62474467  0.55017114  0.47923579
   0.4004876   0.24138406]] Reward -16910.0615937 Loss 3817.31982422
Episode 0 Step 621 Action [[ 0.33426594  0.49538659  0.50339638  0.41042642  0.3587547   0.37450576
   0.61968958  0.40882731]] Reward -16933.6836769 Loss 1426.92114258
Episode 0 Step 622 Action [[ 0.31512758  0.49796191  0.47291837  0.30986131  0.33519675  0.53930116
   0.46104649  0.47125585]] Reward -16959.1543564 Loss 157.021575928
Episode 0 Step 623 Action [[ 0.27152813  0.56420212  0.52638437  0.49366748  0.58318446  0.43740951
   0.56720996  0.46608548]] Reward -16986.6566792 Loss 255.542694092
Episode 0 Step 624 Action [[ 0.45643967  0.38707446  0.38198716  0.6464018   0.45802691  0.54421353
   0.40138228  0.45387323]] Reward -17013.218438 Loss 1771.60620117
Episode 0 Step 625 Action [[ 0.19812857  0.23704306  0.50159653  0.4399515   0.2326013   0.35599975
   0.54743761  0.60538564]] Reward -17033.6910782 Loss 2416.1628418
Episode 0 Step 626 Action [[ 0.62516572  0.48252173  0.40950849  0.36184015  0.5827306   0.50305798
   0.54077549  0.46390573]] Reward -17062.7215291 Loss 1078.55102539
Episode 0 Step 627 Action [[ 0.49896859  0.41245396  0.42779457  0.56289946  0.50289046  0.3851623
   0.5676116   0.37803095]] Reward -17087.627892 Loss 51.4112510681
Episode 0 Step 628 Action [[ 0.45114945  0.54054829  0.54111156  0.49593728  0.5168471   0.56099389
   0.20325232  0.35683449]] Reward -17117.0150382 Loss 408.896118164
Episode 0 Step 629 Action [[ 0.49219686  0.41527665  0.40760162  0.38418661  0.34859303  0.51640313
   0.58234342  0.50413014]] Reward -17142.1213352 Loss 1870.56176758
Episode 0 Step 630 Action [[ 0.53546368  0.62222371  0.57231414  0.69759422  0.56730913  0.40080956
   0.53466418  0.5565734 ]] Reward -17169.540267 Loss 5388.86328125
Episode 0 Step 631 Action [[ 0.34800315  0.48335506  0.39489951  0.43973553  0.51441299  0.51376882
   0.49347298  0.56166875]] Reward -17198.2643303 Loss 7936.56347656
Episode 0 Step 632 Action [[ 0.34917296  0.52558023  0.65015319  0.48799159  0.36433114  0.36610082
   0.45027545  0.49812908]] Reward -17222.3389925 Loss 2249.88671875
Episode 0 Step 633 Action [[ 0.53735209  0.54894129  0.52148773  0.35706603  0.57750075  0.48306837
   0.40864463  0.36708583]] Reward -17251.6380105 Loss 665.763916016
Episode 0 Step 634 Action [[ 0.56844853  0.45680493  0.48735909  0.43770227  0.39420816  0.5092491
   0.41781261  0.45075484]] Reward -17277.2205955 Loss 12091.0634766
Episode 0 Step 635 Action [[ 0.47152353  0.51029799  0.43896393  0.38251901  0.49356875  0.4169757
   0.40070888  0.61194027]] Reward -17302.8556661 Loss 41060.3476562
Episode 0 Step 636 Action [[ 0.54740955  0.49897913  0.62147009  0.47860093  0.54994191  0.47884188
   0.5386965   0.52418798]] Reward -17330.6532118 Loss 75148.8125
Episode 0 Step 637 Action [[ 0.5594273   0.50147444  0.40188976  0.60704462  0.35372831  0.38571473
   0.35785077  0.49919919]] Reward -17353.1110613 Loss 47833.6015625
Episode 0 Step 638 Action [[ 0.45596286  0.49423118  0.29762575  0.46797027  0.43148887  0.51305663
   0.43954511  0.28952337]] Reward -17379.563066 Loss 1262.11425781
Episode 0 Step 639 Action [[ 0.48502392  0.61860304  0.52466979  0.51231535  0.6085922   0.46907922
   0.58086356  0.47878437]] Reward -17409.2061258 Loss 27612.6523438
Episode 0 Step 640 Action [[ 0.33271641  0.58709611  0.35542464  0.38227436  0.52418529  0.46918883
   0.55133448  0.47186451]] Reward -17436.9433142 Loss 65364.9179688
Episode 0 Step 641 Action [[ 0.25687674  0.33318082  0.44178672  0.37707072  0.40333432  0.39420929
   0.54831752  0.46506707]] Reward -17460.3074562 Loss 23794.21875
Episode 0 Step 642 Action [[ 0.3857634   0.41636227  0.38890181  0.43621974  0.26209548  0.4821337
   0.48858147  0.47136304]] Reward -17482.4288078 Loss 3559.18847656
Episode 0 Step 643 Action [[ 0.47346302  0.45446596  0.39049078  0.43351993  0.59946148  0.43218672
   0.59222     0.62145222]] Reward -17509.584702 Loss 12428.0605469
Episode 0 Step 644 Action [[ 0.40707054  0.37409722  0.48493036  0.63357436  0.58012308  0.32344066
   0.54907049  0.54118131]] Reward -17534.571311 Loss 30.5710449219
Episode 0 Step 645 Action [[ 0.52218405  0.64300566  0.4294307   0.45383074  0.51748876  0.55654593
   0.40775463  0.46502255]] Reward -17564.0564164 Loss 9543.5
Episode 0 Step 646 Action [[ 0.55998937  0.59420239  0.57370916  0.43293507  0.47066849  0.38894011
   0.56420041  0.59415095]] Reward -17589.9844493 Loss 1828.44775391
Episode 0 Step 647 Action [[ 0.40529861  0.54290145  0.48683854  0.59076821  0.43162154  0.44952432
   0.62253453  0.50925371]] Reward -17615.625532 Loss 5597.68457031
Episode 0 Step 648 Action [[ 0.49931113  0.50608131  0.25811995  0.4446388   0.29130491  0.59435518
   0.52200526  0.62057976]] Reward -17641.1900049 Loss 17952.5605469
Episode 0 Step 649 Action [[ 0.51331742  0.47936424  0.34751903  0.35706967  0.62164146  0.50025455
   0.48331929  0.36230228]] Reward -17670.6627428 Loss 215.044784546
Episode 0 Step 650 Action [[ 0.49627338  0.49056468  0.47117056  0.38761353  0.42034473  0.38151839
   0.45913765  0.43199104]] Reward -17694.4395671 Loss 13157.0917969
Episode 0 Step 651 Action [[ 0.64471032  0.55688376  0.55713952  0.47003849  0.41043826  0.47486643
   0.44652506  0.38414185]] Reward -17719.755668 Loss 2542.11303711
Episode 0 Step 652 Action [[ 0.57786911  0.37514898  0.48390131  0.2576706   0.51123564  0.60106148
   0.50647463  0.44039839]] Reward -17748.4137869 Loss 8420.39941406
Episode 0 Step 653 Action [[ 0.45733409  0.38182683  0.44299958  0.46327911  0.42613256  0.46882402
   0.49103779  0.46535796]] Reward -17772.3554341 Loss 13815.4716797
Episode 0 Step 654 Action [[ 0.50200251  0.41667374  0.46529492  0.36168918  0.4167546   0.3962419
   0.57991     0.50009346]] Reward -17795.4379792 Loss 565.085327148
Episode 0 Step 655 Action [[ 0.56390469  0.55991638  0.37749886  0.48004429  0.55352323  0.34950222
   0.65709833  0.76569694]] Reward -17819.9891474 Loss 6204.8671875
Episode 0 Step 656 Action [[ 0.62203955  0.44926592  0.60722854  0.54817098  0.3646364   0.39870298
   0.60130612  0.54123691]] Reward -17842.8882009 Loss 2611.28979492
Episode 0 Step 657 Action [[ 0.35313917  0.40508203  0.53536943  0.56761356  0.49875927  0.49892037
   0.58279526  0.43922388]] Reward -17870.0988049 Loss 6763.90771484
Episode 0 Step 658 Action [[ 0.39663023  0.63799816  0.39220875  0.40765963  0.55451768  0.52010627
   0.53996051  0.49881865]] Reward -17899.4291951 Loss 34375.9023438
Episode 0 Step 659 Action [[ 0.59621015  0.40126646  0.41689165  0.39641425  0.66068345  0.33510203
   0.25955412  0.34437924]] Reward -17926.3615751 Loss 8219.40234375
Episode 0 Step 660 Action [[ 0.46098065  0.36605129  0.51171604  0.48890515  0.32834125  0.74620764
   0.39891988  0.53581582]] Reward -17954.505534 Loss 18498.8320312
Episode 0 Step 661 Action [[ 0.53223127  0.30399565  0.44048245  0.43890288  0.50043276  0.47012576
   0.5191239   0.46890914]] Reward -17980.7014479 Loss 37670.6953125
Episode 0 Step 662 Action [[ 0.44410454  0.4847011   0.63186069  0.52058385  0.44677826  0.4304685
   0.5184745   0.59007149]] Reward -18006.2907572 Loss 3467.78271484
Episode 0 Step 663 Action [[ 0.55096275  0.65535996  0.25598323  0.53112433  0.48320171  0.58019338
   0.46628202  0.54966751]] Reward -18034.7734524 Loss 14114.6298828
Episode 0 Step 664 Action [[ 0.44899271  0.52014544  0.58416808  0.27900236  0.35254676  0.40476174
   0.4406497   0.40296008]] Reward -18058.8963125 Loss 22898.1796875
Episode 0 Step 665 Action [[ 0.63415967  0.42147859  0.47147581  0.5018547   0.4921778   0.61835579
   0.48710317  0.41356687]] Reward -18087.3694989 Loss 3173.89892578
Episode 0 Step 666 Action [[ 0.37717709  0.49895368  0.4079443   0.52287069  0.40964599  0.52049274
   0.44383221  0.358707  ]] Reward -18113.1940424 Loss 36027.4335938
Episode 0 Step 667 Action [[ 0.59441756  0.4135962   0.59346555  0.27952792  0.47217903  0.31139985
   0.40101352  0.4171853 ]] Reward -18137.1636039 Loss 10045.3681641
Episode 0 Step 668 Action [[ 0.58902338  0.61203214  0.51346947  0.48916467  0.55280481  0.44250479
   0.42857877  0.3401419 ]] Reward -18164.1278282 Loss 11100.9355469
Episode 0 Step 669 Action [[ 0.34586767  0.61023711  0.49120282  0.38838982  0.59610524  0.52591823
   0.42097439  0.62748028]] Reward -18193.5790976 Loss 21052.828125
Episode 0 Step 670 Action [[ 0.56464097  0.39801031  0.48597322  0.4500943   0.54431714  0.36631991
   0.36858177  0.35367815]] Reward -18218.51233 Loss 9212.38867188
Episode 0 Step 671 Action [[ 0.37880918  0.43179878  0.51217735  0.33735978  0.4752358   0.42118666
   0.58253761  0.36943572]] Reward -18243.5551735 Loss 47174.5507812
Episode 0 Step 672 Action [[ 0.51525213  0.43904454  0.57371765  0.63802738  0.36376921  0.42051352
   0.27959042  0.51313714]] Reward -18266.3938456 Loss 11648.671875
Episode 0 Step 673 Action [[ 0.52979362  0.31277918  0.54135631  0.39547547  0.48753104  0.53660178
   0.50331837  0.71581096]] Reward -18294.0658 Loss 15285.2646484
Episode 0 Step 674 Action [[ 0.56123068  0.34055563  0.31824508  0.50178752  0.53170544  0.55032875
   0.41577782  0.3439642 ]] Reward -18321.7460044 Loss 21329.1523438
Episode 0 Step 675 Action [[ 0.49796168  0.52668795  0.59356105  0.20317377  0.75183833  0.34720758
   0.46288358  0.51728025]] Reward -18351.3423696 Loss 2369.74902344
Episode 0 Step 676 Action [[ 0.43246235  0.54172857  0.47332174  0.53890053  0.31865136  0.49270185
   0.30912084  0.41177547]] Reward -18374.3903352 Loss 23597.0742188
Episode 0 Step 677 Action [[ 0.44733598  0.38644619  0.47436699  0.50444945  0.55028843  0.49263388
   0.47396121  0.28343096]] Reward -18401.700661 Loss 175.756347656
Episode 0 Step 678 Action [[ 0.33609457  0.36276645  0.58278876  0.72388442  0.52326371  0.5153665
   0.37873248  0.31793591]] Reward -18429.5537993 Loss 21243.5175781
Episode 0 Step 679 Action [[ 0.51078356  0.43805202  0.25301464  0.35737969  0.46609695  0.41774553
   0.59958891  0.52690173]] Reward -18455.3965588 Loss 15899.6259766
Episode 0 Step 680 Action [[ 0.50894867  0.50932784  0.40189765  0.5105081   0.55103972  0.57604895
   0.40919269  0.49700239]] Reward -18485.1293608 Loss 1511.7878418
Episode 0 Step 681 Action [[ 0.42113233  0.36830584  0.41090233  0.44760923  0.24973002  0.40499425
   0.28112901  0.56940991]] Reward -18506.5773456 Loss 10750.046875
Episode 0 Step 682 Action [[ 0.36486471  0.64223615  0.51311361  0.39559092  0.50401472  0.44964358
   0.44229632  0.49548086]] Reward -18534.0066346 Loss 791.169921875
Episode 0 Step 683 Action [[ 0.35867836  0.4910114   0.31778972  0.38063491  0.44989893  0.40085401
   0.34415886  0.44676607]] Reward -18558.2428877 Loss 14882.3671875
Episode 0 Step 684 Action [[ 0.46259164  0.49793653  0.47005078  0.43192827  0.48818153  0.27898546
   0.54228345  0.27129724]] Reward -18581.1653604 Loss 4289.68359375
Episode 0 Step 685 Action [[ 0.43829847  0.39803757  0.42336394  0.54833394  0.51150177  0.48383216
   0.4280966   0.51677575]] Reward -18607.5599119 Loss 2834.36865234
Episode 0 Step 686 Action [[ 0.38246253  0.55440705  0.58831016  0.60152997  0.51249982  0.47069758
   0.48120743  0.51757527]] Reward -18635.2633563 Loss 6553.79443359
Episode 0 Step 687 Action [[ 0.66049676  0.52130729  0.47292308  0.43820529  0.45470302  0.50444007
   0.38798516  0.62020373]] Reward -18662.7763182 Loss 39.8056716919
Episode 0 Step 688 Action [[ 0.58409391  0.52678507  0.5019673   0.4083009   0.5220975   0.50294554
   0.51977596  0.45016439]] Reward -18691.190537 Loss 4100.09277344
Episode 0 Step 689 Action [[ 0.51757223  0.51994871  0.48334435  0.57055473  0.55958934  0.60691297
   0.31194557  0.54281782]] Reward -18721.551976 Loss 197.943664551
Episode 0 Step 690 Action [[ 0.5745662   0.38598385  0.45929873  0.52817186  0.31523495  0.41649952
   0.49485653  0.49082111]] Reward -18744.5882276 Loss 5849.50048828
Episode 0 Step 691 Action [[ 0.47356826  0.48763988  0.48207569  0.4914263   0.56535137  0.39458934
   0.462875    0.48005179]] Reward -18772.0430825 Loss 2255.36645508
Episode 0 Step 692 Action [[ 0.47908956  0.55166688  0.42415178  0.45753087  0.35259107  0.43144096
   0.55180903  0.58182337]] Reward -18796.4541461 Loss 3420.93652344
Episode 0 Step 693 Action [[ 0.48508609  0.25940906  0.40153455  0.41584687  0.48861455  0.5741613
   0.33060116  0.35206088]] Reward -18824.4679139 Loss 3336.81298828
Episode 0 Step 694 Action [[ 0.44687597  0.4287752   0.46255776  0.41615964  0.55743576  0.46071481
   0.36988766  0.45945385]] Reward -18852.0592763 Loss 1282.04321289
Episode 0 Step 695 Action [[ 0.43669046  0.45741098  0.43923501  0.2274196   0.46419463  0.60537817
   0.41191967  0.51508688]] Reward -18880.2785073 Loss 2324.99951172
Episode 0 Step 696 Action [[ 0.49894069  0.50610035  0.39244216  0.35591641  0.49973135  0.37412274
   0.46178898  0.41234266]] Reward -18904.0383042 Loss 4512.44238281
Episode 0 Step 697 Action [[ 0.36104915  0.42495173  0.25089264  0.38033071  0.48274991  0.50476144
   0.54767544  0.46982824]] Reward -18928.9553432 Loss 17646.1054688
Episode 0 Step 698 Action [[ 0.60264058  0.40183117  0.41507119  0.59479986  0.47488452  0.33842182
   0.48421672  0.42398501]] Reward -18951.3107433 Loss 1817.28149414
Episode 0 Step 699 Action [[ 0.42185627  0.54266641  0.4179907   0.43987165  0.60912135  0.56584859
   0.53001975  0.44724913]] Reward -18981.3407461 Loss 6219.76074219
Episode 0 Step 700 Action [[ 0.50392462  0.58689805  0.32251807  0.43255905  0.40398836  0.46060129
   0.49520302  0.51243943]] Reward -19005.9125766 Loss 1116.83520508
Episode 0 Step 701 Action [[ 0.40802152  0.58380743  0.55509781  0.44914778  0.58083064  0.50011194
   0.6034446   0.35218478]] Reward -19034.7946315 Loss 4980.37890625
Episode 0 Step 702 Action [[ 0.2705018   0.52255391  0.52856307  0.48569555  0.55631998  0.48485004
   0.46606608  0.36982098]] Reward -19062.790742 Loss 2121.859375
Episode 0 Step 703 Action [[ 0.41617875  0.45715086  0.37500416  0.49274422  0.4561714   0.44016053
   0.475744    0.6509458 ]] Reward -19087.9144447 Loss 2533.50048828
Episode 0 Step 704 Action [[ 0.37768743  0.65022019  0.48020152  0.34891567  0.45971849  0.49962658
   0.30432159  0.39406809]] Reward -19115.1484179 Loss 4341.06933594
Episode 0 Step 705 Action [[ 0.43137059  0.46089737  0.53470639  0.37556106  0.49392682  0.19086852
   0.35189856  0.59294445]] Reward -19136.7383856 Loss 44.9451522827
Episode 0 Step 706 Action [[ 0.52416737  0.61019267  0.32169265  0.43907945  0.4557577   0.38581224
   0.48470547  0.54937592]] Reward -19160.540111 Loss 2947.77441406
Episode 0 Step 707 Action [[ 0.49249889  0.47212803  0.62049683  0.46630743  0.45594147  0.4432104
   0.49719583  0.35217765]] Reward -19185.8989434 Loss 972.412109375
Episode 0 Step 708 Action [[ 0.48434627  0.41606604  0.37049412  0.46368464  0.413559    0.58688389
   0.5560112   0.34808646]] Reward -19212.3240451 Loss 624.292480469
Episode 0 Step 709 Action [[ 0.42133647  0.51976202  0.38839783  0.29035638  0.45754782  0.44178966
   0.58873383  0.46023359]] Reward -19237.540312 Loss 169.497299194
Episode 0 Step 710 Action [[ 0.64404012  0.45951423  0.6050475   0.57404167  0.48152413  0.58739467
   0.35652894  0.58213143]] Reward -19265.3117784 Loss 1050.05834961
Episode 0 Step 711 Action [[ 0.38335121  0.24155962  0.42195761  0.45193005  0.50424273  0.57325512
   0.32116096  0.52230821]] Reward -19292.9609435 Loss 1842.35974121
Episode 0 Step 712 Action [[ 0.53131563  0.55909813  0.38901289  0.40347647  0.2957373   0.54271247
   0.40802427  0.42287543]] Reward -19317.3607239 Loss 2547.64794922
Episode 0 Step 713 Action [[ 0.40089012  0.32800207  0.54731391  0.34569971  0.50272181  0.54570999
   0.45679657  0.37754198]] Reward -19344.8987009 Loss 11568.4707031
Episode 0 Step 714 Action [[ 0.52135089  0.52921222  0.49589129  0.53778901  0.48418782  0.50270853
   0.35048708  0.47291873]] Reward -19371.3620725 Loss 1005.22265625
Episode 0 Step 715 Action [[ 0.56811842  0.53993611  0.55464483  0.63809306  0.41513614  0.27344977
   0.3140343   0.5107962 ]] Reward -19393.5727052 Loss 10390.8955078
Episode 0 Step 716 Action [[ 0.54259521  0.40646809  0.37695685  0.62836321  0.34380453  0.39930575
   0.43419336  0.513124  ]] Reward -19416.774809 Loss 14199.4179688
Episode 0 Step 717 Action [[ 0.26207922  0.36457455  0.40619255  0.50588014  0.63991221  0.47450572
   0.67239665  0.47188749]] Reward -19446.9191696 Loss 2855.77783203
Episode 0 Step 718 Action [[ 0.4001217   0.53683281  0.49705088  0.42937361  0.37894567  0.57494962
   0.43810215  0.54929427]] Reward -19474.8883914 Loss 16050.4042969
Episode 0 Step 719 Action [[ 0.33272084  0.43838161  0.34303237  0.464954    0.53637073  0.56777898
   0.47580366  0.27852218]] Reward -19504.1796182 Loss 2258.22314453
Episode 0 Step 720 Action [[ 0.56673491  0.43399493  0.46158848  0.55262278  0.4443823   0.33172428
   0.43203031  0.3892531 ]] Reward -19528.0451688 Loss 17593.65625
Episode 0 Step 721 Action [[ 0.41061449  0.47339312  0.55145063  0.42461113  0.35473723  0.47129346
   0.45933986  0.38599061]] Reward -19553.4462804 Loss 41.3928070068
Episode 0 Step 722 Action [[ 0.47347982  0.43956282  0.30086736  0.55640554  0.68254644  0.3932911
   0.52335589  0.40822777]] Reward -19581.8691412 Loss 13987.6113281
Episode 0 Step 723 Action [[ 0.38483472  0.46007811  0.49079131  0.37883569  0.49170926  0.53042378
   0.40477809  0.39897606]] Reward -19610.3449468 Loss 2910.04907227
Episode 0 Step 724 Action [[ 0.42385783  0.56286089  0.57976268  0.37088334  0.43245985  0.43193163
   0.49702895  0.63212754]] Reward -19636.0647269 Loss 6617.53710938
Episode 0 Step 725 Action [[ 0.42718526  0.60206696  0.55642242  0.50218266  0.54779032  0.38887603
   0.43491092  0.49141868]] Reward -19662.5505301 Loss 10095.6894531
Episode 0 Step 726 Action [[ 0.45166805  0.35766521  0.4690705   0.40665272  0.51375464  0.61032911
   0.43705713  0.55656537]] Reward -19691.5958623 Loss 814.219970703
Episode 0 Step 727 Action [[ 0.37767769  0.45977363  0.60461761  0.40933216  0.53095097  0.69238724
   0.48832932  0.29414112]] Reward -19722.7636584 Loss 4419.03417969
Episode 0 Step 728 Action [[ 0.47447446  0.46895792  0.47054835  0.35094889  0.45193507  0.62365782
   0.33003936  0.47782375]] Reward -19750.8837827 Loss 21.8063392639
Episode 0 Step 729 Action [[ 0.25440245  0.3815269   0.4351429   0.29034306  0.60959617  0.46412083
   0.56286526  0.33682395]] Reward -19778.2234298 Loss 4633.89746094
Episode 0 Step 730 Action [[ 0.53339763  0.40097049  0.48537515  0.55954422  0.36526661  0.68004911
   0.51933483  0.46113193]] Reward -19804.6731988 Loss 103.939117432
Episode 0 Step 731 Action [[ 0.52654051  0.39334738  0.43308628  0.40865043  0.52889523  0.51631083
   0.50893837  0.6197739 ]] Reward -19831.8908175 Loss 4113.06689453
Episode 0 Step 732 Action [[ 0.44229567  0.52472447  0.33598233  0.46104076  0.34660402  0.32390441
   0.43099427  0.44386248]] Reward -19852.698534 Loss 1119.3737793
Episode 0 Step 733 Action [[ 0.51439021  0.40134211  0.52745802  0.40334096  0.43065828  0.44371887
   0.46952065  0.44422432]] Reward -19877.3764997 Loss 916.813293457
Episode 0 Step 734 Action [[ 0.5968293   0.48957167  0.61735478  0.60783498  0.53602607  0.4753587
   0.39289651  0.72484948]] Reward -19904.758918 Loss 2578.96777344
Episode 0 Step 735 Action [[ 0.46960597  0.32956263  0.41315962  0.49794228  0.49800916  0.66410442
   0.4790514   0.54768796]] Reward -19934.5694703 Loss 1291.91625977
Episode 0 Step 736 Action [[ 0.40970522  0.58768598  0.61999019  0.34559534  0.4503195   0.41296022
   0.46289767  0.50682538]] Reward -19960.7289003 Loss 884.474914551
Episode 0 Step 737 Action [[ 0.38470363  0.50604801  0.38361216  0.41833556  0.51758776  0.33304424
   0.5273153   0.42175536]] Reward -19985.0437558 Loss 2738.11914062
Episode 0 Step 738 Action [[ 0.48636318  0.32344674  0.36986576  0.4176715   0.50079265  0.28972856
   0.54522507  0.45342517]] Reward -20007.655835 Loss 101.665130615
Episode 0 Step 739 Action [[ 0.54268417  0.43202596  0.3386016   0.23732587  0.49111329  0.46371389
   0.38323186  0.58289721]] Reward -20033.2029471 Loss 1702.33544922
Episode 0 Step 740 Action [[ 0.37269516  0.37250634  0.73811929  0.5018171   0.59449829  0.24749691
   0.47463981  0.37050258]] Reward -20056.839583 Loss 1244.41455078
Episode 0 Step 741 Action [[ 0.40281059  0.42740052  0.46685641  0.56269172  0.68001566  0.4463286
   0.46898002  0.48111915]] Reward -20085.3319717 Loss 562.280883789
Episode 0 Step 742 Action [[ 0.66935328  0.32757972  0.58243822  0.34173044  0.41283156  0.47899351
   0.50890739  0.37850962]] Reward -20110.6185326 Loss 2655.06762695
Episode 0 Step 743 Action [[ 0.42998115  0.5785375   0.29173958  0.61278421  0.54974398  0.38784568
   0.55571658  0.45949565]] Reward -20136.0249736 Loss 820.03137207
Episode 0 Step 744 Action [[ 0.52612974  0.56775402  0.47836471  0.41613982  0.56424397  0.39757286
   0.42438266  0.42665132]] Reward -20163.2824748 Loss 618.508483887
Episode 0 Step 745 Action [[ 0.59624453  0.38121099  0.51807224  0.58928883  0.4123101   0.47289159
   0.68441332  0.52435287]] Reward -20188.5164822 Loss 1565.52648926
Episode 0 Step 746 Action [[ 0.30244288  0.52269743  0.46132729  0.46010418  0.3859609   0.67513977
   0.30462821  0.40500093]] Reward -20217.6209939 Loss 354.749053955
Episode 0 Step 747 Action [[ 0.52138723  0.53922441  0.46892783  0.62320818  0.3805851   0.40520225
   0.60244459  0.46393301]] Reward -20241.9262573 Loss 832.918884277
Episode 0 Step 748 Action [[ 0.48266943  0.3741721   0.42251753  0.50385874  0.47504109  0.27538455
   0.56881165  0.37921475]] Reward -20265.6924666 Loss 1673.05554199
Episode 0 Step 749 Action [[ 0.63130344  0.38878067  0.28881958  0.42297034  0.37597764  0.39337894
   0.36859629  0.3904396 ]] Reward -20289.3261682 Loss 29.5146064758
Episode 0 Step 750 Action [[ 0.54605847  0.42516639  0.34294944  0.47244511  0.50685574  0.33922086
   0.40155602  0.56972225]] Reward -20314.060859 Loss 1824.86303711
Episode 0 Step 751 Action [[ 0.51432928  0.39252444  0.34404719  0.60760767  0.43022233  0.55567713
   0.43101099  0.49039717]] Reward -20340.9857777 Loss 1585.97412109
Episode 0 Step 752 Action [[ 0.47131795  0.26821156  0.43020576  0.40550031  0.48015695  0.47135256
   0.37627538  0.44595364]] Reward -20367.8216251 Loss 394.96182251
Episode 0 Step 753 Action [[ 0.40062289  0.32753716  0.24790673  0.29620218  0.5801649   0.54771705
   0.42691274  0.40234735]] Reward -20396.737674 Loss 2515.63623047
Episode 0 Step 754 Action [[ 0.41356457  0.47728807  0.48910285  0.51970117  0.52617549  0.59864957
   0.44676446  0.437264  ]] Reward -20425.7707416 Loss 332.51864624
Episode 0 Step 755 Action [[ 0.59421219  0.43966607  0.55005065  0.48814153  0.4644897   0.28493314
   0.41666212  0.38845517]] Reward -20448.8887763 Loss 779.664794922
Episode 0 Step 756 Action [[ 0.47956713  0.37132601  0.49880902  0.45299755  0.31538267  0.39989981
   0.39064187  0.49350952]] Reward -20471.2444378 Loss 544.279907227
Episode 0 Step 757 Action [[ 0.28794772  0.39433242  0.50608272  0.37042534  0.46566905  0.27579797
   0.44418786  0.28291164]] Reward -20494.0654949 Loss 265.665130615
Episode 0 Step 758 Action [[ 0.37686668  0.33567746  0.38878173  0.42740326  0.52188826  0.49416744
   0.42282915  0.58372253]] Reward -20520.6130364 Loss 1159.93530273
Episode 0 Step 759 Action [[ 0.43098744  0.5145557   0.54194878  0.53616587  0.46551218  0.39828787
   0.64049086  0.62921678]] Reward -20545.486893 Loss 399.141967773
Episode 0 Step 760 Action [[ 0.55015677  0.36402027  0.35293789  0.54710385  0.36222675  0.46312095
   0.61638972  0.49874437]] Reward -20569.216953 Loss 206.851776123
Episode 0 Step 761 Action [[ 0.31971356  0.32433195  0.39783361  0.30725284  0.54996596  0.45094808
   0.64895461  0.37454752]] Reward -20596.3926095 Loss 559.621154785
Episode 0 Step 762 Action [[ 0.56238104  0.45983484  0.488799    0.58338109  0.42284505  0.54042869
   0.47887964  0.53035238]] Reward -20622.6690377 Loss 66.9462738037
Episode 0 Step 763 Action [[ 0.56816236  0.36886647  0.58962419  0.35480317  0.58182018  0.36669899
   0.35868947  0.50519061]] Reward -20649.4576741 Loss 692.128967285
Episode 0 Step 764 Action [[ 0.44756105  0.34640603  0.39253039  0.40363514  0.54432124  0.41846049
   0.47440957  0.53797254]] Reward -20675.2575788 Loss 1407.97021484
Episode 0 Step 765 Action [[ 0.37386861  0.2893935   0.58673293  0.40624778  0.58432225  0.65058183
   0.34622266  0.48195708]] Reward -20705.8900483 Loss 424.992126465
Episode 0 Step 766 Action [[ 0.40107222  0.52251121  0.42131964  0.48142687  0.59994594  0.49145762
   0.48590155  0.41285182]] Reward -20734.1518826 Loss 118.16796875
Episode 0 Step 767 Action [[ 0.52294592  0.55070363  0.42543624  0.35322578  0.55071193  0.490933
   0.37711055  0.44328799]] Reward -20761.9342323 Loss 613.381164551
Episode 0 Step 768 Action [[ 0.3689777   0.35229123  0.61994675  0.51774358  0.39000807  0.41241672
   0.37520677  0.45539191]] Reward -20785.197188 Loss 32.1528549194
Episode 0 Step 769 Action [[ 0.56692031  0.34956577  0.3370113   0.24387015  0.57031091  0.45528771
   0.33342814  0.48813054]] Reward -20811.9535028 Loss 655.444335938
Episode 0 Step 770 Action [[ 0.3717914   0.47948677  0.53852332  0.57799915  0.41923436  0.71954211
   0.5346726   0.41411985]] Reward -20840.599902 Loss 696.117919922
Episode 0 Step 771 Action [[ 0.46728634  0.63295342  0.46429869  0.57865859  0.58972446  0.33963354
   0.54121265  0.47946619]] Reward -20866.8536559 Loss 34.7378692627
Episode 0 Step 772 Action [[ 0.36818697  0.50483087  0.53418091  0.5608417   0.48148793  0.35084777
   0.38852741  0.48641291]] Reward -20891.9580229 Loss 768.364013672
Episode 0 Step 773 Action [[ 0.42425461  0.33955756  0.40921451  0.38174755  0.53207495  0.49521125
   0.33976684  0.36144828]] Reward -20919.9408729 Loss 219.901245117
Episode 0 Step 774 Action [[ 0.57173502  0.59074627  0.3624752   0.55572824  0.48722946  0.55681806
   0.43708137  0.37549385]] Reward -20948.1951447 Loss 458.538482666
Episode 0 Step 775 Action [[ 0.29962408  0.5942888   0.3822163   0.26150267  0.39885219  0.46428326
   0.46045486  0.45003209]] Reward -20973.8713703 Loss 2123.16723633
Episode 0 Step 776 Action [[ 0.54221152  0.43359174  0.47371783  0.35314128  0.64264794  0.33651279
   0.51164927  0.46882679]] Reward -21000.1477584 Loss 2535.16503906
Episode 0 Step 777 Action [[ 0.30208625  0.50401254  0.49450208  0.29683111  0.42392421  0.53173457
   0.50367022  0.48099041]] Reward -21025.9326474 Loss 56.8324737549
Episode 0 Step 778 Action [[ 0.48346588  0.49021922  0.41008691  0.44779061  0.4467213   0.5585324
   0.21599467  0.43062596]] Reward -21051.7140242 Loss 2181.30957031
Episode 0 Step 779 Action [[ 0.35758395  0.48748689  0.59127224  0.43736651  0.50472968  0.4052386
   0.3331744   0.52662716]] Reward -21076.788564 Loss 3663.44482422
Episode 0 Step 780 Action [[ 0.39977607  0.59081789  0.44543507  0.60403316  0.5944699   0.41068203
   0.53890633  0.41419898]] Reward -21103.5608138 Loss 209.789978027
Episode 0 Step 781 Action [[ 0.6163187   0.34139785  0.44774473  0.36657418  0.52938205  0.3646049
   0.66757033  0.64152796]] Reward -21128.7207735 Loss 4822.30859375
Episode 0 Step 782 Action [[ 0.44790116  0.51122465  0.47578511  0.58783361  0.53777051  0.56584637
   0.54201136  0.43904563]] Reward -21157.5207745 Loss 2572.90039062
Episode 0 Step 783 Action [[ 0.53992893  0.466478    0.33766417  0.44037684  0.31746437  0.42562749
   0.42615358  0.3878136 ]] Reward -21180.3980599 Loss 600.700683594
Episode 0 Step 784 Action [[ 0.58656441  0.19782914  0.36500277  0.4959356   0.38776447  0.50732349
   0.49986259  0.44352317]] Reward -21204.9960642 Loss 207.002288818
Episode 0 Step 785 Action [[ 0.458649    0.48822106  0.43331172  0.50744092  0.39430788  0.61729431
   0.49142638  0.52029018]] Reward -21232.7450385 Loss 874.097900391
Episode 0 Step 786 Action [[ 0.45455218  0.46900882  0.45453835  0.48776761  0.38809689  0.47983811
   0.50961618  0.41986827]] Reward -21258.236564 Loss 423.0390625
Episode 0 Step 787 Action [[ 0.57455832  0.55031957  0.49731675  0.4533355   0.39946345  0.45691668
   0.3808514   0.43899579]] Reward -21283.8790932 Loss 58.7014541626
Episode 0 Step 788 Action [[ 0.48138756  0.47348095  0.39582492  0.69181743  0.35748054  0.45989757
   0.47728901  0.44886575]] Reward -21308.1791294 Loss 808.20489502
Episode 0 Step 789 Action [[ 0.2428508   0.51172736  0.46366499  0.45007922  0.62899451  0.54973398
   0.49680605  0.33926433]] Reward -21340.0222225 Loss 1456.32373047
Episode 0 Step 790 Action [[ 0.62780007  0.54329802  0.52567994  0.25700133  0.39715198  0.45065078
   0.58565505  0.49762154]] Reward -21366.0241815 Loss 79.7693634033
Episode 0 Step 791 Action [[ 0.46796749  0.41177974  0.52696278  0.41178882  0.41213514  0.57840711
   0.44162752  0.4569639 ]] Reward -21392.8014277 Loss 814.722717285
Episode 0 Step 792 Action [[ 0.4863174   0.51573297  0.45616087  0.48266566  0.27507742  0.50555711
   0.47662738  0.33714082]] Reward -21415.9560692 Loss 87.8983688354
Episode 0 Step 793 Action [[ 0.51788582  0.51442334  0.35581153  0.49997705  0.42458556  0.41616368
   0.54464705  0.60424754]] Reward -21440.1230174 Loss 684.800170898
Episode 0 Step 794 Action [[ 0.41025353  0.41119068  0.49424309  0.36335346  0.41161093  0.37615662
   0.54541614  0.36821363]] Reward -21463.7401014 Loss 1191.09936523
Episode 0 Step 795 Action [[ 0.61048806  0.403777    0.28518381  0.69908476  0.48277172  0.50511124
   0.32698704  0.55369052]] Reward -21489.6638794 Loss 70.0473556519
Episode 0 Step 796 Action [[ 0.52539605  0.34195157  0.4934502   0.5114948   0.4988063   0.39133814
   0.55980928  0.46839   ]] Reward -21515.6813848 Loss 1447.60302734
Episode 0 Step 797 Action [[ 0.2836129   0.47683622  0.52864691  0.44243306  0.52792351  0.4721642
   0.41700609  0.3164698 ]] Reward -21544.0534653 Loss 1776.06274414
Episode 0 Step 798 Action [[ 0.38575873  0.69003351  0.40718187  0.44981037  0.51508349  0.44884797
   0.47985267  0.49758325]] Reward -21571.7339241 Loss 422.791687012
Episode 0 Step 799 Action [[ 0.39085921  0.4219176   0.57167929  0.46668731  0.6178985   0.35454602
   0.44112585  0.39668358]] Reward -21599.0429531 Loss 79.6234664917
Episode 0 Step 800 Action [[ 0.40172051  0.46858562  0.39175081  0.48542626  0.33896759  0.32560421
   0.44505941  0.40836651]] Reward -21620.6607825 Loss 230.916534424
Episode 0 Step 801 Action [[ 0.51281174  0.38645761  0.4982906   0.49395499  0.40145183  0.48528257
   0.41592519  0.40891431]] Reward -21646.190094 Loss 118.338668823
Episode 0 Step 802 Action [[ 0.46330214  0.54089195  0.54308318  0.47016459  0.43197275  0.4491201
   0.62778192  0.40235356]] Reward -21672.285353 Loss 54.6403236389
Episode 0 Step 803 Action [[ 0.62738433  0.44950457  0.15148376  0.48174241  0.47576614  0.48626023
   0.45893563  0.35853545]] Reward -21698.2953087 Loss 78.4940795898
Episode 0 Step 804 Action [[ 0.46382869  0.39577097  0.42359563  0.52303266  0.35642245  0.48818172
   0.28414941  0.52789887]] Reward -21722.9581738 Loss 88.8503494263
Episode 0 Step 805 Action [[ 0.40780935  0.34436221  0.69035335  0.56806789  0.54979513  0.61663324
   0.25896794  0.46373435]] Reward -21753.9912015 Loss 54.518371582
Episode 0 Step 806 Action [[ 0.45021202  0.54908158  0.46664954  0.57391276  0.34733156  0.51030567
   0.50417632  0.32117401]] Reward -21780.0577744 Loss 155.150085449
Episode 0 Step 807 Action [[ 0.47453458  0.46675397  0.50692117  0.38866405  0.53915864  0.48983076
   0.32070365  0.66681252]] Reward -21809.222762 Loss 101.941772461
Episode 0 Step 808 Action [[ 0.49261503  0.46003365  0.47570134  0.531917    0.48800863  0.28689015
   0.46497719  0.50457508]] Reward -21833.2137352 Loss 77.9007568359
Episode 0 Step 809 Action [[ 0.52794851  0.29417812  0.36475274  0.54894358  0.47850938  0.31466752
   0.46808794  0.42213363]] Reward -21856.9279219 Loss 406.923706055
Episode 0 Step 810 Action [[ 0.57892474  0.41644633  0.51767345  0.36758957  0.4120308   0.39742747
   0.4448733   0.37884118]] Reward -21881.9370041 Loss 1075.07128906
Episode 0 Step 811 Action [[ 0.34585723  0.58514629  0.38347606  0.42438407  0.30103676  0.41959318
   0.50995799  0.5037679 ]] Reward -21904.7966149 Loss 2243.13354492
Episode 0 Step 812 Action [[ 0.58872358  0.54768435  0.45127359  0.36752009  0.55338993  0.40322626
   0.31711461  0.33685507]] Reward -21931.4969612 Loss 4404.39648438
Episode 0 Step 813 Action [[ 0.23656603  0.29870478  0.31147082  0.32138401  0.31759782  0.24154349
   0.55348615  0.36143295]] Reward -21949.8767543 Loss 5154.09960938
Episode 0 Step 814 Action [[ 0.53790006  0.51882197  0.47175905  0.58108947  0.48707347  0.50488303
   0.50528464  0.42341143]] Reward -21976.1679632 Loss 2456.04003906
Episode 0 Step 815 Action [[ 0.47503656  0.40246648  0.6266253   0.6441042   0.45070625  0.38693817
   0.25205028  0.56082752]] Reward -22000.8425355 Loss 1675.90588379
Episode 0 Step 816 Action [[ 0.33257359  0.52564284  0.41024193  0.57389163  0.51303489  0.62750743
   0.40419475  0.48912269]] Reward -22031.3804051 Loss 13360.15625
Episode 0 Step 817 Action [[ 0.37946016  0.58605696  0.50976338  0.47799169  0.58334344  0.4516383
   0.44029282  0.35778964]] Reward -22060.8959812 Loss 31431.9804688
Episode 0 Step 818 Action [[ 0.34840132  0.52781537  0.41556917  0.68915612  0.57455345  0.44319197
   0.43730511  0.22207284]] Reward -22089.4228876 Loss 30820.21875
Episode 0 Step 819 Action [[ 0.37965534  0.40407501  0.41236355  0.39503347  0.51594349  0.51086558
   0.44764916  0.41675774]] Reward -22118.6352476 Loss 121.783454895
Episode 0 Step 820 Action [[ 0.52675227  0.44293778  0.29792737  0.47418943  0.37084058  0.59047856
   0.47029244  0.4902337 ]] Reward -22145.6647934 Loss 28432.4296875
Episode 0 Step 821 Action [[ 0.50153466  0.60051642  0.61267275  0.62013361  0.58858106  0.45289177
   0.26702496  0.3588463 ]] Reward -22175.2052821 Loss 61394.4375
Episode 0 Step 822 Action [[ 0.57010044  0.48875157  0.5271297   0.5995339   0.58372807  0.48029114
   0.45848704  0.45786946]] Reward -22205.1511363 Loss 38041.4765625
Episode 0 Step 823 Action [[ 0.44123045  0.50138327  0.49433429  0.40431172  0.36621091  0.32056722
   0.50313663  0.61563222]] Reward -22228.9215274 Loss 12731.0595703
Episode 0 Step 824 Action [[ 0.46217667  0.47158344  0.47333065  0.49413171  0.36667402  0.41513449
   0.35483137  0.44335423]] Reward -22253.3923202 Loss 956.385803223
Episode 0 Step 825 Action [[ 0.27247563  0.40326095  0.35452134  0.57823014  0.55372679  0.44482061
   0.3621415   0.46155004]] Reward -22280.9587473 Loss 24442.2753906
Episode 0 Step 826 Action [[ 0.49619739  0.48504882  0.49990193  0.51066361  0.39337237  0.51730445
   0.46796031  0.61318423]] Reward -22308.0374707 Loss 46837.2695312
Episode 0 Step 827 Action [[ 0.43381077  0.60921934  0.41347384  0.51317145  0.47032192  0.45933474
   0.48090101  0.50147712]] Reward -22335.4566891 Loss 41948.859375
Episode 0 Step 828 Action [[ 0.38482525  0.41109186  0.46162213  0.54683165  0.58094855  0.48252179
   0.43719696  0.51017152]] Reward -22364.6846486 Loss 9805.25585938
Episode 0 Step 829 Action [[ 0.41221081  0.50239382  0.43956751  0.43740424  0.30641654  0.4660648
   0.42609829  0.62366345]] Reward -22389.2847869 Loss 131603.46875
Episode 0 Step 830 Action [[ 0.4156644   0.36579933  0.27272146  0.35347135  0.41478877  0.41539898
   0.47916395  0.39534338]] Reward -22413.5401719 Loss 93128.421875
Episode 0 Step 831 Action [[ 0.48307122  0.57101872  0.31496456  0.44979398  0.64650827  0.36323668
   0.44684899  0.36318125]] Reward -22440.8394292 Loss 61316.4726562
Episode 0 Step 832 Action [[ 0.45459829  0.47725464  0.40253218  0.3402096   0.34195106  0.45528474
   0.50097987  0.55654959]] Reward -22464.4572603 Loss 254070.8125
Episode 0 Step 833 Action [[ 0.46234966  0.39725998  0.52478854  0.45842669  0.36109344  0.3659121
   0.63135874  0.32352094]] Reward -22486.4079015 Loss 110.729232788
Episode 0 Step 834 Action [[ 0.30738428  0.5395131   0.55430551  0.32153417  0.39848108  0.45793272
   0.43077165  0.41848918]] Reward -22511.2500524 Loss 257116.703125
Episode 0 Step 835 Action [[ 0.53773006  0.41457622  0.44803511  0.59808586  0.71896303  0.29695953
   0.31665893  0.37077174]] Reward -22537.5798865 Loss 125968.148438
Episode 0 Step 836 Action [[ 0.44904173  0.39595103  0.43958912  0.38165446  0.53116762  0.44112071
   0.62746108  0.39672402]] Reward -22564.1048856 Loss 91454.171875
Episode 0 Step 837 Action [[ 0.45854488  0.55727773  0.35093616  0.30134474  0.4229149   0.40978885
   0.40728644  0.3702303 ]] Reward -22588.05599 Loss 188068.4375
Episode 0 Step 838 Action [[ 0.44723457  0.54314555  0.47181521  0.3528954   0.5856405   0.3451757
   0.38900819  0.49061209]] Reward -22613.3271597 Loss 4201.70507812
Episode 0 Step 839 Action [[ 0.3605886   0.64234406  0.50407642  0.40369557  0.63501518  0.4686828
   0.47447969  0.51008861]] Reward -22641.711506 Loss 90075.046875
Episode 0 Step 840 Action [[ 0.60647015  0.61135371  0.36676978  0.33687961  0.50599668  0.50976539
   0.67534144  0.47403304]] Reward -22668.1956882 Loss 1055.51269531
Episode 0 Step 841 Action [[ 0.55597992  0.38553892  0.46978778  0.55730606  0.49504921  0.33647453
   0.51925642  0.40860193]] Reward -22690.9257679 Loss 106539.164062
Episode 0 Step 842 Action [[ 0.47918112  0.49559967  0.50973673  0.50205015  0.41720193  0.51435971
   0.43202047  0.56732588]] Reward -22716.7203215 Loss 2835.03076172
Episode 0 Step 843 Action [[ 0.33301324  0.4028927   0.41058672  0.52934301  0.49700533  0.48155892
   0.51348639  0.36916199]] Reward -22743.1296593 Loss 71876.546875
Episode 0 Step 844 Action [[ 0.2883824   0.45804804  0.57819524  0.56446922  0.63461371  0.31345307
   0.40276907  0.41132301]] Reward -22770.0672415 Loss 1407.79455566
Episode 0 Step 845 Action [[ 0.49165661  0.40253583  0.37195737  0.45334669  0.54992136  0.22435506
   0.36096533  0.4204866 ]] Reward -22793.7296068 Loss 94047.765625
Episode 0 Step 846 Action [[ 0.39048779  0.34220748  0.46074749  0.72944231  0.46034358  0.57371519
   0.52215746  0.40745853]] Reward -22821.6929327 Loss 4834.44140625
Episode 0 Step 847 Action [[ 0.40609116  0.53749546  0.26421252  0.47049686  0.55766807  0.50369681
   0.68312049  0.58726193]] Reward -22851.3470846 Loss 43826.9453125
Episode 0 Step 848 Action [[ 0.54428887  0.35173976  0.41097802  0.60793016  0.44078693  0.35367271
   0.30869571  0.40704838]] Reward -22875.8675501 Loss 79.7804718018
Episode 0 Step 849 Action [[ 0.3516071   0.35079142  0.47215018  0.55781303  0.4581366   0.43758332
   0.4458231   0.55175321]] Reward -22902.6988929 Loss 53080.4375
Episode 0 Step 850 Action [[ 0.38344176  0.44177777  0.40963711  0.61263112  0.32072122  0.39169442
   0.46716972  0.62310302]] Reward -22926.4913209 Loss 7649.14941406
Episode 0 Step 851 Action [[ 0.4804193   0.462949    0.55851029  0.51187488  0.42844062  0.48842543
   0.51902334  0.47449515]] Reward -22954.5379886 Loss 48160.7421875
Episode 0 Step 852 Action [[ 0.59352302  0.44119004  0.54379831  0.29470499  0.36164765  0.39254783
   0.44824519  0.31849289]] Reward -22979.3903533 Loss 3195.08349609
Episode 0 Step 853 Action [[ 0.48985509  0.4611723   0.56651045  0.41100425  0.4047814   0.63153867
   0.55671165  0.44102791]] Reward -23007.901762 Loss 35590.03125
Episode 0 Step 854 Action [[ 0.54520226  0.64212685  0.54395016  0.43205728  0.50768865  0.50540833
   0.40706916  0.27307637]] Reward -23036.1157966 Loss 297.654174805
Episode 0 Step 855 Action [[ 0.44079214  0.44623841  0.37005139  0.43146522  0.38581846  0.47511558
   0.28017494  0.46357176]] Reward -23060.553039 Loss 33158.46875
Episode 0 Step 856 Action [[ 0.47262906  0.46712713  0.4827188   0.33101225  0.33768136  0.54283382
   0.55395327  0.39563127]] Reward -23085.6137647 Loss 1670.68188477
Episode 0 Step 857 Action [[ 0.27534202  0.63343511  0.53776141  0.59432225  0.44627463  0.31446017
   0.57056639  0.46580122]] Reward -23108.7061182 Loss 28490.2929688
Episode 0 Step 858 Action [[ 0.49267805  0.33212321  0.47659846  0.44083708  0.60325868  0.52669067
   0.56050131  0.51650022]] Reward -23137.9470389 Loss 1281.78991699
Episode 0 Step 859 Action [[ 0.43915549  0.48255822  0.50704381  0.4476288   0.55197246  0.47047701
   0.51038494  0.28685334]] Reward -23165.7563559 Loss 18115.4160156
Episode 0 Step 860 Action [[ 0.35381863  0.3873242   0.4880209   0.59146749  0.40468609  0.45660851
   0.5395635   0.39902964]] Reward -23190.4469419 Loss 4408.23339844
Episode 0 Step 861 Action [[ 0.48568282  0.5490863   0.40027338  0.26229103  0.36510389  0.33340223
   0.39204996  0.50301119]] Reward -23213.2448569 Loss 20133.4335938
Episode 0 Step 862 Action [[ 0.54548114  0.52678876  0.45733757  0.50556839  0.50710626  0.49140439
   0.41829659  0.39672645]] Reward -23240.0980208 Loss 427.993499756
Episode 0 Step 863 Action [[ 0.48454034  0.47726853  0.57252955  0.39325093  0.51793195  0.49516282
   0.2506898   0.51749441]] Reward -23267.7883491 Loss 17390.203125
Episode 0 Step 864 Action [[ 0.50672671  0.49192138  0.28424523  0.55676861  0.37256599  0.47993428
   0.61968829  0.50809886]] Reward -23291.6769663 Loss 533.615905762
Episode 0 Step 865 Action [[ 0.46177184  0.49865514  0.49426193  0.54143651  0.53182943  0.4604691
   0.57439997  0.45460565]] Reward -23319.1856599 Loss 10785.4335938
Episode 0 Step 866 Action [[ 0.43121165  0.52399372  0.53283536  0.3571801   0.47152875  0.37372629
   0.52693491  0.6895685 ]] Reward -23344.7334955 Loss 826.848144531
Episode 0 Step 867 Action [[ 0.69240611  0.43139638  0.50608047  0.35365797  0.28781533  0.44157007
   0.62347849  0.56925265]] Reward -23367.2770646 Loss 7744.53515625
Episode 0 Step 868 Action [[ 0.55784807  0.35229354  0.36130062  0.45512039  0.42274249  0.27772166
   0.33774411  0.45495913]] Reward -23388.2003215 Loss 75.3064498901
Episode 0 Step 869 Action [[ 0.35511339  0.5025265   0.46531094  0.44313     0.4351163   0.4156947
   0.43922501  0.39216824]] Reward -23412.5938213 Loss 7001.49316406
Episode 0 Step 870 Action [[ 0.54760815  0.43404467  0.57598245  0.46092514  0.48930875  0.49664969
   0.56575188  0.4768356 ]] Reward -23439.4604175 Loss 144.661865234
Episode 0 Step 871 Action [[ 0.38165094  0.65132426  0.45473419  0.3962438   0.45318623  0.56067536
   0.467931    0.4845346 ]] Reward -23467.2072296 Loss 5770.45410156
Episode 0 Step 872 Action [[ 0.67893212  0.54887764  0.43656648  0.40515114  0.57840273  0.31731987
   0.58901652  0.51003722]] Reward -23492.3525463 Loss 216.558914185
Episode 0 Step 873 Action [[ 0.35492722  0.43739157  0.51762052  0.46117345  0.35699124  0.23472547
   0.40437196  0.45067981]] Reward -23512.107648 Loss 3975.44433594
Episode 0 Step 874 Action [[ 0.49023009  0.44878586  0.3243519   0.43476085  0.42283311  0.42398793
   0.34862791  0.78282372]] Reward -23535.8980769 Loss 86.0508499146
Episode 0 Step 875 Action [[ 0.37906256  0.48183979  0.49518394  0.46696747  0.52013305  0.5935889
   0.49699174  0.3775399 ]] Reward -23564.8214121 Loss 2618.71728516
Episode 0 Step 876 Action [[ 0.39642817  0.35063991  0.427064    0.47506699  0.30160275  0.6283925
   0.3985527   0.26172798]] Reward -23590.1941927 Loss 135.166946411
Episode 0 Step 877 Action [[ 0.50861441  0.45115109  0.40470516  0.46498288  0.46604147  0.58911689
   0.52459831  0.40495249]] Reward -23618.1069992 Loss 2668.68823242
Episode 0 Step 878 Action [[ 0.35966079  0.44055826  0.46497881  0.4044383   0.47788086  0.46018358
   0.48466607  0.36030673]] Reward -23644.2193666 Loss 82.814414978
Episode 0 Step 879 Action [[ 0.66960555  0.4667381   0.41691282  0.43427782  0.54042234  0.34714938
   0.44985943  0.41299079]] Reward -23669.140433 Loss 3137.89550781
Episode 0 Step 880 Action [[ 0.41752692  0.50573259  0.47652541  0.59779044  0.49817385  0.42925329
   0.4435136   0.37642536]] Reward -23694.9978101 Loss 1379.47827148
Episode 0 Step 881 Action [[ 0.49947246  0.53561677  0.4365223   0.32637955  0.57024099  0.55609899
   0.45984333  0.3324781 ]] Reward -23725.0019208 Loss 2877.32763672
Episode 0 Step 882 Action [[ 0.35422305  0.29168543  0.36242275  0.44754305  0.50145844  0.4679083
   0.42619351  0.29118053]] Reward -23750.6294021 Loss 883.143066406
Episode 0 Step 883 Action [[ 0.45197292  0.4252653   0.39781224  0.48201666  0.39752418  0.45246002
   0.52468179  0.61407363]] Reward -23774.7637942 Loss 2307.13232422
Episode 0 Step 884 Action [[ 0.41832587  0.36141554  0.49159265  0.48404788  0.53179664  0.51911548
   0.45733426  0.41176821]] Reward -23802.5925887 Loss 1591.46118164
Episode 0 Step 885 Action [[ 0.45701444  0.29175395  0.58863165  0.37953912  0.50648751  0.39480433
   0.4524938   0.49386658]] Reward -23828.1098063 Loss 1468.78491211
Episode 0 Step 886 Action [[ 0.53230237  0.52220452  0.28438457  0.46098377  0.42817572  0.4817288
   0.42570317  0.45661205]] Reward -23853.142197 Loss 2614.95898438
Episode 0 Step 887 Action [[ 0.42011551  0.34286293  0.47203193  0.42488959  0.4790631   0.57370893
   0.43635623  0.61095422]] Reward -23880.7645997 Loss 1666.49707031
Episode 0 Step 888 Action [[ 0.42178089  0.52428419  0.41612304  0.56528495  0.48740817  0.38530999
   0.54979098  0.4584603 ]] Reward -23905.5651927 Loss 2491.70678711
Episode 0 Step 889 Action [[ 0.50495827  0.32917566  0.51951396  0.47008796  0.62524592  0.45378662
   0.49087296  0.58403279]] Reward -23934.256613 Loss 1156.6998291
Episode 0 Step 890 Action [[ 0.51124125  0.55579486  0.47311416  0.82052651  0.40233637  0.58864451
   0.42043807  0.57116698]] Reward -23961.9303166 Loss 2883.12817383
Episode 0 Step 891 Action [[ 0.39526185  0.43915446  0.44608195  0.45717613  0.48976694  0.33353989
   0.394034    0.64621107]] Reward -23988.0655133 Loss 679.438354492
Episode 0 Step 892 Action [[ 0.47432023  0.36803547  0.53791766  0.44633283  0.41532308  0.53550506
   0.52501181  0.41774746]] Reward -24015.8343754 Loss 1831.22265625
Episode 0 Step 893 Action [[ 0.46091692  0.47030515  0.55562759  0.59527831  0.47600567  0.55328272
   0.31478279  0.48118554]] Reward -24044.8174597 Loss 246.1612854
Episode 0 Step 894 Action [[ 0.4760613   0.46369931  0.5153655   0.52259224  0.51224183  0.3758392
   0.34750803  0.29431444]] Reward -24071.6598151 Loss 2138.36547852
Episode 0 Step 895 Action [[ 0.37565875  0.42873617  0.54342678  0.5441288   0.52998676  0.39237996
   0.53735252  0.35442797]] Reward -24099.009634 Loss 105.511451721
Episode 0 Step 896 Action [[ 0.38143274  0.38470408  0.5501956   0.44300713  0.58980655  0.5576884
   0.51824486  0.54124577]] Reward -24130.1493096 Loss 1224.89208984
Episode 0 Step 897 Action [[ 0.37766124  0.39385187  0.64117297  0.44532041  0.38066106  0.38653319
   0.42692939  0.59405224]] Reward -24154.6143527 Loss 77.2477111816
Episode 0 Step 898 Action [[ 0.52137275  0.29344699  0.40334881  0.48517327  0.37777546  0.55015458
   0.54172803  0.31588971]] Reward -24180.5208911 Loss 945.764953613
Episode 0 Step 899 Action [[ 0.42245397  0.44622003  0.52502747  0.41455772  0.53150467  0.44986067
   0.48124502  0.45845933]] Reward -24208.1260717 Loss 84.8179473877
Episode 0 Step 900 Action [[ 0.59426291  0.44341064  0.42139246  0.49918572  0.37736239  0.32951723
   0.44060574  0.42443   ]] Reward -24230.3513339 Loss 1204.83569336
Episode 0 Step 901 Action [[ 0.45349433  0.48212997  0.50668345  0.45402475  0.6403394   0.47333262
   0.50419386  0.39797459]] Reward -24260.0475472 Loss 131.278320312
Episode 0 Step 902 Action [[ 0.37492572  0.53688129  0.41215863  0.52111982  0.35959657  0.58619915
   0.49123116  0.56781293]] Reward -24286.6539273 Loss 1087.4465332
Episode 0 Step 903 Action [[ 0.42260739  0.52757099  0.44072692  0.51135572  0.35375352  0.31863514
   0.38196521  0.38572558]] Reward -24308.8883913 Loss 314.054016113
Episode 0 Step 904 Action [[ 0.50292426  0.32599631  0.4986225   0.44104084  0.43187569  0.31739167
   0.35473885  0.45083382]] Reward -24332.1639423 Loss 609.18182373
Episode 0 Step 905 Action [[ 0.41526194  0.54011995  0.3573073   0.38965076  0.54049863  0.51957143
   0.40605553  0.43814991]] Reward -24360.7015863 Loss 429.715240479
Episode 0 Step 906 Action [[ 0.51548657  0.47808715  0.37909086  0.47899516  0.31641033  0.34049037
   0.43082763  0.52065683]] Reward -24381.8015292 Loss 210.554290771
Episode 0 Step 907 Action [[ 0.59244815  0.48026902  0.49620319  0.42910762  0.46582367  0.43541879
   0.526141    0.46495567]] Reward -24407.5481622 Loss 318.721984863
Episode 0 Step 908 Action [[ 0.52886571  0.2915485   0.50730892  0.47661038  0.46865392  0.52170241
   0.51905111  0.55720891]] Reward -24434.1587552 Loss 74.1516036987
Episode 0 Step 909 Action [[ 0.43110332  0.38597221  0.64884276  0.34452078  0.37819357  0.45087314
   0.42984632  0.44606606]] Reward -24458.8142976 Loss 124.745613098
Episode 0 Step 910 Action [[ 0.51814034  0.58662245  0.43810471  0.41884975  0.58419709  0.47945997
   0.44723996  0.46868716]] Reward -24486.8741429 Loss 112.884399414
Episode 0 Step 911 Action [[ 0.54167093  0.44789544  0.48721212  0.5074237   0.52717638  0.48113834
   0.41888016  0.44799584]] Reward -24513.7018233 Loss 37.5953025818
Episode 0 Step 912 Action [[ 0.4953022   0.37648786  0.46796493  0.30283469  0.53255588  0.53381207
   0.45246938  0.38127092]] Reward -24541.683603 Loss 215.109405518
Episode 0 Step 913 Action [[ 0.3923663   0.38009552  0.37199876  0.50962452  0.64397718  0.61862772
   0.47162192  0.59393178]] Reward -24572.0439823 Loss 140.742401123
Episode 0 Step 914 Action [[ 0.43727508  0.48213857  0.43792934  0.4064679   0.37714071  0.41700463
   0.5518271   0.32414884]] Reward -24595.389038 Loss 95.574508667
Episode 0 Step 915 Action [[ 0.42382347  0.37657075  0.37256038  0.45867389  0.55091201  0.50562819
   0.37441451  0.31459337]] Reward -24622.5765807 Loss 80.9005203247
Episode 0 Step 916 Action [[ 0.30033594  0.41324775  0.47749984  0.49225004  0.23727619  0.52275244
   0.55570918  0.44641435]] Reward -24645.283615 Loss 104.721130371
Episode 0 Step 917 Action [[ 0.45720161  0.54425236  0.19365875  0.53973547  0.54536076  0.42667573
   0.39542014  0.47555867]] Reward -24671.4347543 Loss 97.4688720703
Episode 0 Step 918 Action [[ 0.50125297  0.4289271   0.42944234  0.51952677  0.40031474  0.32694442
   0.45179746  0.43907579]] Reward -24694.1934236 Loss 123.550521851
Episode 0 Step 919 Action [[ 0.55479983  0.43053803  0.59041639  0.54645006  0.59929177  0.4475731
   0.43765966  0.47137054]] Reward -24723.078234 Loss 69.3333358765
Episode 0 Step 920 Action [[ 0.34208832  0.46874802  0.46542226  0.49699853  0.45810855  0.47765518
   0.48235903  0.36143218]] Reward -24750.09641 Loss 107.428588867
Episode 0 Step 921 Action [[ 0.50407021  0.51189276  0.53997008  0.21934976  0.64958455  0.4281339
   0.38965511  0.41006042]] Reward -24779.8221501 Loss 80.0130767822
Episode 0 Step 922 Action [[ 0.40635802  0.4401425   0.51849553  0.43961799  0.2795874   0.43241345
   0.31840598  0.30152577]] Reward -24801.6107095 Loss 162.880264282
Episode 0 Step 923 Action [[ 0.49496991  0.3933847   0.52429839  0.67497531  0.29710683  0.51195043
   0.4509362   0.33074191]] Reward -24825.0391496 Loss 111.308837891
Episode 0 Step 924 Action [[ 0.35451774  0.49468992  0.56296515  0.55647846  0.52310341  0.28265059
   0.55497598  0.59976716]] Reward -24850.0791366 Loss 126.137893677
Episode 0 Step 925 Action [[ 0.53877146  0.47900436  0.71386919  0.48746136  0.44536005  0.5011905
   0.35435121  0.31059029]] Reward -24878.1537606 Loss 106.956848145
Episode 0 Step 926 Action [[ 0.25824181  0.29006392  0.40944223  0.54357497  0.34624343  0.54695274
   0.49076619  0.41778428]] Reward -24903.7919342 Loss 148.986831665
Episode 0 Step 927 Action [[ 0.41819276  0.40560587  0.51394149  0.43697799  0.61382196  0.41323786
   0.47298002  0.37258037]] Reward -24932.523044 Loss 231.147842407
Episode 0 Step 928 Action [[ 0.26118476  0.54658096  0.43880821  0.48422129  0.55004005  0.46824272
   0.47709913  0.3149838 ]] Reward -24960.8885 Loss 101.198326111
Episode 0 Step 929 Action [[ 0.32604763  0.21852213  0.3899476   0.31335208  0.40617157  0.3733387
   0.54307885  0.58690286]] Reward -24984.0532067 Loss 265.67376709
Episode 0 Step 930 Action [[ 0.5485141   0.40361354  0.27796193  0.39308803  0.3615001   0.58343319
   0.49650216  0.44693593]] Reward -25009.3514615 Loss 84.014755249
Episode 0 Step 931 Action [[ 0.39754414  0.58609801  0.52695462  0.30817047  0.32766605  0.49082656
   0.43775317  0.48114444]] Reward -25033.5049859 Loss 217.172714233
Episode 0 Step 932 Action [[ 0.48979648  0.46562378  0.5677134   0.41361085  0.43914106  0.45735246
   0.32266993  0.50975208]] Reward -25058.1566055 Loss 72.3399353027
Episode 0 Step 933 Action [[ 0.47308785  0.40850872  0.46506731  0.39943971  0.27664312  0.32487491
   0.47938293  0.4455812 ]] Reward -25077.4355464 Loss 275.307617188
Episode 0 Step 934 Action [[ 0.43234327  0.40729076  0.54590592  0.58584431  0.32280093  0.42714719
   0.54028168  0.35416048]] Reward -25099.4847963 Loss 38.4705200195
Episode 0 Step 935 Action [[ 0.19822365  0.40642771  0.43107234  0.56652771  0.41043395  0.3727057
   0.38305315  0.45858243]] Reward -25122.7141376 Loss 454.49105835
Episode 0 Step 936 Action [[ 0.50957558  0.50877528  0.28496604  0.64411754  0.37125214  0.48984151
   0.41449425  0.37247753]] Reward -25147.7013365 Loss 193.749053955
Episode 0 Step 937 Action [[ 0.39226288  0.47810501  0.30537884  0.43662883  0.35378343  0.50660145
   0.48107644  0.44866468]] Reward -25173.4529297 Loss 133.671386719
Episode 0 Step 938 Action [[ 0.39640939  0.63422922  0.43408917  0.51023162  0.18626312  0.45795896
   0.39232685  0.57079422]] Reward -25195.8471896 Loss 204.936828613
Episode 0 Step 939 Action [[ 0.36054487  0.48178432  0.31266026  0.5457417   0.39132143  0.52780569
   0.58477039  0.48008219]] Reward -25222.1729058 Loss 69.7804107666
Episode 0 Step 940 Action [[ 0.47220183  0.60095539  0.37764072  0.37594517  0.49084572  0.35517801
   0.63137467  0.42586129]] Reward -25247.9781794 Loss 138.306549072
Episode 0 Step 941 Action [[ 0.32741598  0.32387805  0.49000822  0.23034194  0.35263083  0.51765477
   0.37429915  0.59253104]] Reward -25273.0161745 Loss 55.7770767212
Episode 0 Step 942 Action [[ 0.45960796  0.36099895  0.40848747  0.52437825  0.49766385  0.40514899
   0.33224214  0.5077638 ]] Reward -25297.2509889 Loss 107.014427185
Episode 0 Step 943 Action [[ 0.46146615  0.43458685  0.4309135   0.44091865  0.4260999   0.30379642
   0.5859115   0.37750139]] Reward -25319.4173919 Loss 102.315795898
Episode 0 Step 944 Action [[ 0.32983637  0.48927096  0.46461007  0.3460934   0.48966646  0.66184216
   0.47993752  0.49918579]] Reward -25349.0391779 Loss 160.443771362
Episode 0 Step 945 Action [[ 0.53791591  0.43323622  0.54316986  0.49860562  0.30214752  0.44927296
   0.38207787  0.43144881]] Reward -25371.4140559 Loss 110.330917358
Episode 0 Step 946 Action [[ 0.34652486  0.62064362  0.55537433  0.5616371   0.44689297  0.44827387
   0.41497446  0.50325649]] Reward -25397.2641759 Loss 101.687347412
Episode 0 Step 947 Action [[ 0.49597329  0.64350419  0.56446909  0.51590437  0.44399119  0.35859787
   0.47275904  0.50798188]] Reward -25422.2275058 Loss 180.9347229
Episode 0 Step 948 Action [[ 0.5613189   0.60648839  0.50045953  0.48186624  0.32235077  0.4668827
   0.40526616  0.46201043]] Reward -25446.8794078 Loss 43.0299835205
Episode 0 Step 949 Action [[ 0.392356    0.24972843  0.35945391  0.51108798  0.46127439  0.42338051
   0.53973782  0.613467  ]] Reward -25471.7369925 Loss 656.787353516
Episode 0 Step 950 Action [[ 0.55997376  0.49427425  0.40921837  0.49129398  0.48254919  0.36390415
   0.47020505  0.49298924]] Reward -25496.9041678 Loss 276.715698242
Episode 0 Step 951 Action [[ 0.47617202  0.36758325  0.52687678  0.54768445  0.49653825  0.47557598
   0.46732269  0.42709931]] Reward -25524.1852764 Loss 438.041625977
Episode 0 Step 952 Action [[ 0.48351545  0.67591217  0.40783061  0.4199018   0.37604463  0.54348489
   0.44419501  0.54824876]] Reward -25551.3921639 Loss 787.086303711
Episode 0 Step 953 Action [[ 0.50413293  0.5766158   0.44981468  0.41752202  0.25782534  0.45382011
   0.58764808  0.33185072]] Reward -25574.4293804 Loss 73.8622741699
Episode 0 Step 954 Action [[ 0.32364358  0.54785516  0.41763009  0.50346457  0.40777769  0.47117715
   0.30246708  0.57087246]] Reward -25599.837017 Loss 524.117614746
Episode 0 Step 955 Action [[ 0.36254183  0.46528896  0.47319439  0.42569668  0.39261695  0.36944244
   0.4508261   0.44982075]] Reward -25623.3666892 Loss 122.493003845
Episode 0 Step 956 Action [[ 0.37298606  0.49459703  0.45815054  0.35595368  0.43833765  0.54107588
   0.49942405  0.58533616]] Reward -25650.4066057 Loss 325.462097168
Episode 0 Step 957 Action [[ 0.38810893  0.36076095  0.63346155  0.59467387  0.54024141  0.44147797
   0.44966543  0.53926728]] Reward -25677.0747479 Loss 729.802734375
Episode 0 Step 958 Action [[ 0.49534984  0.46402683  0.39231765  0.60565109  0.52838182  0.41288432
   0.43062125  0.45773934]] Reward -25703.4763867 Loss 231.502853394
Episode 0 Step 959 Action [[ 0.34427688  0.39679313  0.38195084  0.30255472  0.40155664  0.52468816
   0.52162125  0.65240556]] Reward -25730.0562118 Loss 450.763549805
Episode 0 Step 960 Action [[ 0.55656858  0.33984432  0.43874722  0.42485684  0.57790016  0.43491862
   0.295623    0.44938782]] Reward -25757.0243553 Loss 440.814208984
Episode 0 Step 961 Action [[ 0.36356183  0.43917603  0.34240111  0.41935094  0.35935109  0.50513376
   0.51145839  0.4589805 ]] Reward -25781.3487007 Loss 51.1294708252
Episode 0 Step 962 Action [[ 0.29122331  0.37389195  0.57059263  0.53173691  0.51355141  0.31636171
   0.48125042  0.31240587]] Reward -25805.4127965 Loss 359.865783691
Episode 0 Step 963 Action [[ 0.64437015  0.41661685  0.42776016  0.40847387  0.53823724  0.33671565
   0.44188362  0.32218019]] Reward -25830.4189452 Loss 101.609710693
Episode 0 Step 964 Action [[ 0.44530748  0.46961718  0.49499806  0.56323981  0.39172338  0.45550371
   0.43180966  0.3715212 ]] Reward -25855.0269753 Loss 161.457489014
Episode 0 Step 965 Action [[ 0.375998    0.49236794  0.50471116  0.29790773  0.40745328  0.46203859
   0.43048508  0.48091589]] Reward -25880.6822211 Loss 111.880828857
Episode 0 Step 966 Action [[ 0.56301688  0.48556106  0.41015393  0.45440835  0.34156299  0.3677189
   0.37894738  0.41079579]] Reward -25902.378404 Loss 190.288909912
Episode 0 Step 967 Action [[ 0.3812868   0.27916644  0.48647264  0.58884544  0.53929768  0.33196069
   0.39515841  0.43687492]] Reward -25926.6136004 Loss 402.03414917
Episode 0 Step 968 Action [[ 0.42385668  0.44440082  0.44934313  0.51811025  0.38858544  0.48649099
   0.44913067  0.33896554]] Reward -25952.0383983 Loss 182.080200195
Episode 0 Step 969 Action [[ 0.44478915  0.44888127  0.49473983  0.41456551  0.36512711  0.39711128
   0.49588374  0.41549795]] Reward -25975.8731596 Loss 67.4171905518
Episode 0 Step 970 Action [[ 0.41637971  0.54116906  0.2906469   0.40169397  0.49818672  0.48672509
   0.45519341  0.44683945]] Reward -26002.7989739 Loss 74.4411621094
Episode 0 Step 971 Action [[ 0.58513587  0.29396899  0.47866041  0.41739329  0.44110756  0.35829819
   0.39314041  0.38312973]] Reward -26026.050142 Loss 87.7013092041
Episode 0 Step 972 Action [[ 0.3560735   0.58695462  0.44683449  0.4121088   0.26912059  0.56467026
   0.5793509   0.45492119]] Reward -26050.4901822 Loss 62.5584335327
Episode 0 Step 973 Action [[ 0.3660257   0.43024725  0.42678634  0.56831194  0.33477928  0.4165582
   0.48197189  0.57687157]] Reward -26072.8663968 Loss 42.1425437927
Episode 0 Step 974 Action [[ 0.37034122  0.58135073  0.33220025  0.53690387  0.44393926  0.51144645
   0.24613442  0.5767786 ]] Reward -26099.5664362 Loss 43.9034042358
Episode 0 Step 975 Action [[ 0.31785279  0.31947499  0.44884044  0.57026717  0.40683116  0.42468947
   0.58360925  0.51886302]] Reward -26124.075725 Loss 53.602973938
Episode 0 Step 976 Action [[ 0.2913966   0.58115857  0.59457107  0.32500377  0.42171664  0.27232841
   0.49148171  0.33444062]] Reward -26147.793167 Loss 57.8095092773
Episode 0 Step 977 Action [[ 0.30738737  0.35028722  0.67901867  0.34161956  0.42578188  0.33172764
   0.56375304  0.45377621]] Reward -26171.2244626 Loss 98.8773498535
Episode 0 Step 978 Action [[ 0.55067119  0.46970594  0.36983818  0.36916301  0.47994178  0.4857345
   0.37805824  0.29599875]] Reward -26197.0621073 Loss 251.747924805
Episode 0 Step 979 Action [[ 0.55960414  0.48060857  0.49875333  0.41455426  0.38746234  0.41089015
   0.31945435  0.31558085]] Reward -26220.1888779 Loss 69.2388153076
Episode 0 Step 980 Action [[ 0.38642006  0.60675135  0.40880395  0.41126555  0.6577175   0.45848667
   0.40800391  0.3585049 ]] Reward -26248.8810698 Loss 325.655426025
Episode 0 Step 981 Action [[ 0.59754079  0.51289944  0.52379706  0.25257071  0.46635953  0.26637872
   0.31526997  0.46584037]] Reward -26271.0850413 Loss 105.563270569
Episode 0 Step 982 Action [[ 0.38777921  0.32223681  0.48480876  0.47174815  0.39847039  0.49550094
   0.50052582  0.3890721 ]] Reward -26294.6016459 Loss 180.968444824
Episode 0 Step 983 Action [[ 0.36764521  0.56082026  0.46659382  0.34868206  0.52553222  0.45219478
   0.47547884  0.43313302]] Reward -26320.7201116 Loss 132.338088989
Episode 0 Step 984 Action [[ 0.56288855  0.3969563   0.38502601  0.25816988  0.35232347  0.5334433
   0.50246695  0.1974449 ]] Reward -26344.3063239 Loss 95.2699203491
Episode 0 Step 985 Action [[ 0.40814049  0.52499314  0.43599248  0.41178854  0.49427365  0.45178813
   0.56314522  0.55199439]] Reward -26368.8555765 Loss 279.937316895
Episode 0 Step 986 Action [[ 0.45066487  0.35558933  0.46786726  0.31018342  0.55413518  0.42252412
   0.39321879  0.70174719]] Reward -26393.8432887 Loss 339.501190186
Episode 0 Step 987 Action [[ 0.45396196  0.4279671   0.34364176  0.23884402  0.56594718  0.4239926
   0.33817991  0.60972686]] Reward -26418.6354286 Loss 98.9696273804
Episode 0 Step 988 Action [[ 0.50175091  0.43427438  0.36816242  0.44594488  0.54627225  0.48409144
   0.47674458  0.50619799]] Reward -26443.659542 Loss 132.495574951
Episode 0 Step 989 Action [[ 0.46316678  0.32599879  0.4832657   0.61239132  0.34268298  0.53998227
   0.46302488  0.45021932]] Reward -26466.8230886 Loss 229.597106934
Episode 0 Step 990 Action [[ 0.39059371  0.29747075  0.38888939  0.35543172  0.35438927  0.42891815
   0.3760075   0.34698832]] Reward -26489.2262504 Loss 91.4531936646
Episode 0 Step 991 Action [[ 0.52528818  0.44343419  0.51005315  0.52456603  0.59818244  0.49604779
   0.49165503  0.44473548]] Reward -26517.337069 Loss 503.625488281
Episode 0 Step 992 Action [[ 0.38893381  0.50560044  0.46737921  0.46076252  0.44090106  0.51414782
   0.5616063   0.53187793]] Reward -26543.7119465 Loss 293.278503418
Episode 0 Step 993 Action [[ 0.41473692  0.48728393  0.50124286  0.35708781  0.55412019  0.51849221
   0.45231001  0.31860903]] Reward -26572.2081474 Loss 255.449676514
Episode 0 Step 994 Action [[ 0.36885069  0.3109615   0.54417743  0.36756724  0.47286339  0.40392068
   0.48959173  0.49501525]] Reward -26596.5480626 Loss 831.674987793
Episode 0 Step 995 Action [[ 0.57625369  0.5092266   0.4246143   0.37600802  0.52338821  0.56151557
   0.40530166  0.26807513]] Reward -26624.3744341 Loss 196.415985107
Episode 0 Step 996 Action [[ 0.48295016  0.49587353  0.47539755  0.47111203  0.33134442  0.31493084
   0.27571888  0.42324473]] Reward -26644.6947893 Loss 281.201477051
Episode 0 Step 997 Action [[ 0.34581489  0.34598071  0.46369726  0.46760645  0.44893763  0.53237546
   0.31583804  0.42009183]] Reward -26670.6368456 Loss 689.753234863
Episode 0 Step 998 Action [[ 0.39218322  0.57846244  0.40285979  0.49965214  0.32558885  0.50039399
   0.25629345  0.49419227]] Reward -26694.6679227 Loss 203.997161865
Episode 0 Step 999 Action [[ 0.56331344  0.48687578  0.3539672   0.36216411  0.51999503  0.36724227
   0.4623646   0.47555631]] Reward -26719.6725264 Loss 284.342224121
Episode 0 Step 1000 Action [[ 0.27097439  0.43924612  0.47199792  0.48238378  0.53409568  0.46407636
   0.37582708  0.38567276]] Reward -26746.3243787 Loss 1251.33312988
Episode 0 Step 1001 Action [[ 0.37164241  0.41742502  0.50856491  0.40046067  0.62312555  0.47196396
   0.35859441  0.35428167]] Reward -26774.9466181 Loss 1029.37231445
Episode 0 Step 1002 Action [[ 0.52165846  0.52399661  0.43834062  0.28506984  0.42523681  0.60523095
   0.36932382  0.47136025]] Reward -26802.362411 Loss 189.483276367
Episode 0 Step 1003 Action [[ 0.36620805  0.40199503  0.48416202  0.43908095  0.48242097  0.37670734
   0.3039909   0.39833065]] Reward -26825.9131425 Loss 2354.72802734
Episode 0 Step 1004 Action [[ 0.46277147  0.41304748  0.30105533  0.59107873  0.40789071  0.42411283
   0.34760723  0.38022993]] Reward -26848.7623312 Loss 1401.51159668
Episode 0 Step 1005 Action [[ 0.49737603  0.46597422  0.41999962  0.39128273  0.32893647  0.34477588
   0.55544419  0.5359987 ]] Reward -26870.3566823 Loss 227.351837158
Episode 0 Step 1006 Action [[ 0.33226434  0.42906872  0.49595844  0.31318481  0.43576883  0.3216784
   0.65480339  0.40892432]] Reward -26893.1517981 Loss 2539.12890625
Episode 0 Step 1007 Action [[ 0.42826359  0.38892494  0.33886481  0.51756203  0.27944658  0.41609792
   0.52406988  0.31928615]] Reward -26913.6850856 Loss 3756.62353516
Episode 0 Step 1008 Action [[ 0.23890671  0.54911514  0.39688159  0.53758554  0.63752706  0.40700004
   0.52601287  0.58067697]] Reward -26941.4089282 Loss 509.433013916
Episode 0 Step 1009 Action [[ 0.48480277  0.59197592  0.42776376  0.56753634  0.48157122  0.52967467
   0.44708499  0.55670343]] Reward -26969.2584769 Loss 748.018981934
Episode 0 Step 1010 Action [[ 0.33236613  0.42664127  0.35056142  0.49483502  0.47147529  0.33365289
   0.40116477  0.55670133]] Reward -26993.4150562 Loss 3104.31518555
Episode 0 Step 1011 Action [[ 0.54514713  0.4284643   0.4721944   0.3285964   0.48383921  0.31691884
   0.57996161  0.49949581]] Reward -27017.8493142 Loss 1720.3515625
Episode 0 Step 1012 Action [[ 0.42974999  0.44353661  0.44406654  0.33234455  0.54403518  0.55440106
   0.49647838  0.48142243]] Reward -27046.4908535 Loss 71.4954681396
Episode 0 Step 1013 Action [[ 0.35802213  0.39952776  0.54253266  0.46591371  0.30809622  0.37546243
   0.47336432  0.35307127]] Reward -27067.6358286 Loss 1521.96704102
Episode 0 Step 1014 Action [[ 0.62432291  0.42966867  0.41172272  0.69642999  0.22865897  0.33063156
   0.31231473  0.50968106]] Reward -27086.6321712 Loss 1300.04858398
Episode 0 Step 1015 Action [[ 0.42336135  0.41403013  0.41025374  0.5150683   0.44901437  0.55955838
   0.51866301  0.3638685 ]] Reward -27114.5941023 Loss 30.9505138397
Episode 0 Step 1016 Action [[ 0.35966187  0.49681392  0.35288045  0.36311749  0.45692863  0.44572019
   0.45948835  0.3358477 ]] Reward -27140.860903 Loss 1853.85107422
Episode 0 Step 1017 Action [[ 0.59216778  0.54957523  0.41483968  0.49911363  0.55379919  0.42634008
   0.50527084  0.32287323]] Reward -27168.0438239 Loss 4986.35644531
Episode 0 Step 1018 Action [[ 0.53099628  0.48779026  0.50008485  0.45974387  0.47401999  0.53912651
   0.45193537  0.48934901]] Reward -27196.027133 Loss 6648.421875
Episode 0 Step 1019 Action [[ 0.68481814  0.362616    0.43559617  0.45121478  0.46811422  0.68724641
   0.37957654  0.48388967]] Reward -27225.8032504 Loss 4935.69140625
Episode 0 Step 1020 Action [[ 0.47048389  0.49606547  0.2711132   0.48062723  0.52841031  0.46302233
   0.50810838  0.42380989]] Reward -27252.6077435 Loss 812.148071289
Episode 0 Step 1021 Action [[ 0.45364051  0.36143407  0.18824556  0.4476947   0.37562361  0.35394356
   0.45335875  0.39883632]] Reward -27274.390987 Loss 10255.4511719
Episode 0 Step 1022 Action [[ 0.6715769   0.48605084  0.37072937  0.46539104  0.3489001   0.37728868
   0.60946665  0.38433004]] Reward -27296.8851127 Loss 8212.56347656
Episode 0 Step 1023 Action [[ 0.52732826  0.35655492  0.47859825  0.40501601  0.33837759  0.49045711
   0.36757863  0.37762012]] Reward -27321.0700874 Loss 69.7202911377
Episode 0 Step 1024 Action [[ 0.49075354  0.54669933  0.34717662  0.44480345  0.45142344  0.55601369
   0.38170837  0.60792724]] Reward -27348.1919303 Loss 6821.35205078
Episode 0 Step 1025 Action [[ 0.41668764  0.34589073  0.51061792  0.3946384   0.58055689  0.49796623
   0.70685901  0.57526212]] Reward -27376.4138534 Loss 11033.4082031
Episode 0 Step 1026 Action [[ 0.46924528  0.50652389  0.27779267  0.49523569  0.51379704  0.23283975
   0.28198395  0.45586487]] Reward -27398.4826045 Loss 482.042053223
Episode 0 Step 1027 Action [[ 0.51539613  0.25608042  0.53466966  0.55349507  0.52908484  0.50302958
   0.30545316  0.44069935]] Reward -27425.7766114 Loss 3694.84423828
Episode 0 Step 1028 Action [[ 0.38814949  0.52274168  0.67117204  0.35449191  0.67918945  0.46532274
   0.46930226  0.66257386]] Reward -27456.6803312 Loss 6623.45898438
Episode 0 Step 1029 Action [[ 0.5788913   0.5412113   0.37369136  0.2997891   0.35326408  0.54685131
   0.56675197  0.51784161]] Reward -27481.9512274 Loss 7508.30273438
Episode 0 Step 1030 Action [[ 0.21702838  0.33510754  0.29447099  0.44153919  0.28286822  0.37478469
   0.52662664  0.35359747]] Reward -27501.5638441 Loss 1502.65869141
Episode 0 Step 1031 Action [[ 0.42450384  0.4228323   0.41864999  0.47320365  0.50343699  0.3443609
   0.45499554  0.5116737 ]] Reward -27525.2334366 Loss 2158.3762207
Episode 0 Step 1032 Action [[ 0.31273763  0.36617864  0.49925233  0.47646643  0.48892767  0.37116726
   0.38438623  0.63063957]] Reward -27549.4848259 Loss 15159.7685547
Episode 0 Step 1033 Action [[ 0.4593075   0.37706983  0.42894222  0.35290301  0.31870267  0.43848524
   0.4228202   0.48805404]] Reward -27572.0258645 Loss 17400.1992188
Episode 0 Step 1034 Action [[ 0.46983462  0.44948753  0.47185193  0.50703737  0.3928147   0.51110989
   0.36325775  0.36202451]] Reward -27596.9446477 Loss 37.3463172913
Episode 0 Step 1035 Action [[ 0.57525951  0.42575896  0.5221066   0.4796503   0.39168204  0.38492036
   0.56271268  0.47181624]] Reward -27620.2265772 Loss 15224.5068359
Episode 0 Step 1036 Action [[ 0.47750399  0.44284104  0.39857725  0.45368114  0.3153046   0.26852259
   0.6820513   0.40615027]] Reward -27640.0897139 Loss 13793.0751953
Episode 0 Step 1037 Action [[ 0.4317647   0.53693051  0.31223606  0.56089884  0.389431    0.3744672
   0.56683834  0.41532652]] Reward -27663.0436284 Loss 2684.8112793
Episode 0 Step 1038 Action [[ 0.53365618  0.51403171  0.29823954  0.39506697  0.46411071  0.43719201
   0.46772681  0.4533676 ]] Reward -27688.7700238 Loss 3515.90478516
Episode 0 Step 1039 Action [[ 0.44671574  0.4703787   0.43845239  0.4404016   0.41216606  0.34137442
   0.58728968  0.48709865]] Reward -27711.809051 Loss 9445.0546875
Episode 0 Step 1040 Action [[ 0.46452584  0.44535207  0.48421234  0.38680171  0.4114935   0.35957627
   0.44065381  0.40716939]] Reward -27735.1004236 Loss 10760.5458984
Episode 0 Step 1041 Action [[ 0.50983292  0.41335205  0.56040272  0.47042979  0.36557782  0.42290832
   0.3811333   0.407587  ]] Reward -27758.4842196 Loss 5150.72070312
Episode 0 Step 1042 Action [[ 0.51351707  0.26560777  0.4208188   0.43706846  0.33763658  0.68534143
   0.52586389  0.29432725]] Reward -27785.2258589 Loss 47.00573349
Episode 0 Step 1043 Action [[ 0.46354982  0.60247836  0.48007482  0.37270563  0.54591695  0.36348079
   0.5776974   0.41127755]] Reward -27811.1474442 Loss 6032.18554688
Episode 0 Step 1044 Action [[ 0.49576484  0.47845509  0.48383888  0.28962545  0.38570198  0.32551865
   0.4331837   0.57060171]] Reward -27832.9764965 Loss 18373.7695312
Episode 0 Step 1045 Action [[ 0.53923451  0.4599489   0.47233863  0.4018023   0.3622782   0.52524211
   0.26424157  0.50533339]] Reward -27857.0620759 Loss 20909.25
Episode 0 Step 1046 Action [[ 0.47579071  0.41877158  0.54709733  0.3795853   0.47048012  0.60269636
   0.56043513  0.50622061]] Reward -27884.5200355 Loss 1595.0246582
Episode 0 Step 1047 Action [[ 0.46451147  0.50945646  0.39273165  0.36613495  0.47960194  0.5489516
   0.42570575  0.41473366]] Reward -27910.9745175 Loss 9955.27441406
Episode 0 Step 1048 Action [[ 0.52542348  0.39557534  0.45930142  0.30799732  0.47977715  0.51935362
   0.18252373  0.49985844]] Reward -27936.6956853 Loss 51784.5078125
Episode 0 Step 1049 Action [[ 0.52053058  0.67959642  0.38330738  0.51411334  0.47301805  0.27260606
   0.46403362  0.38523401]] Reward -27958.3343376 Loss 102021.835938
Episode 0 Step 1050 Action [[ 0.37762563  0.30271711  0.52929564  0.36917223  0.39455728  0.38748605
   0.44244575  0.37407861]] Reward -27980.7003636 Loss 18808.3554688
Episode 0 Step 1051 Action [[ 0.33416361  0.56230627  0.31310537  0.39267435  0.38494741  0.32180337
   0.35661631  0.45875179]] Reward -28001.7346069 Loss 22163.6132812
Episode 0 Step 1052 Action [[ 0.53969243  0.47178311  0.44443086  0.47833562  0.60897381  0.3863308
   0.42266978  0.30087356]] Reward -28027.7926678 Loss 134603.015625
Episode 0 Step 1053 Action [[ 0.5515147   0.32838317  0.47147876  0.35068817  0.61606676  0.25345561
   0.59458399  0.33467758]] Reward -28051.8084537 Loss 135216.59375
Episode 0 Step 1054 Action [[ 0.49719427  0.43405071  0.60037515  0.39440347  0.26134852  0.49525481
   0.399065    0.55692805]] Reward -28074.2270564 Loss 11175.3212891
Episode 0 Step 1055 Action [[ 0.47197668  0.5405524   0.5323595   0.39335921  0.36477461  0.46932857
   0.44154558  0.23616309]] Reward -28098.0405497 Loss 98238.03125
Episode 0 Step 1056 Action [[ 0.47139948  0.54357378  0.37998264  0.34048906  0.47365592  0.57293758
   0.49319808  0.43676163]] Reward -28125.0473863 Loss 172885.640625
Episode 0 Step 1057 Action [[ 0.56521589  0.65255615  0.43782865  0.34983885  0.45922092  0.51673233
   0.49322273  0.59390206]] Reward -28151.052243 Loss 44786.4453125
Episode 0 Step 1058 Action [[ 0.32893086  0.53749661  0.54558442  0.49911531  0.42650957  0.46713738
   0.31624344  0.49805661]] Reward -28175.4734783 Loss 20344.234375
Episode 0 Step 1059 Action [[ 0.47280701  0.42032401  0.50464892  0.49101367  0.39639121  0.50476154
   0.37289693  0.49912933]] Reward -28200.2050209 Loss 89446.375
Episode 0 Step 1060 Action [[ 0.64105572  0.4091417   0.51267752  0.46453787  0.44145983  0.40142012
   0.38842353  0.57682466]] Reward -28224.3531408 Loss 1936.57519531
Episode 0 Step 1061 Action [[ 0.43060757  0.57505019  0.49292256  0.49979803  0.46755221  0.7082823
   0.51461026  0.34642459]] Reward -28254.7565195 Loss 73282.28125
Episode 0 Step 1062 Action [[ 0.39288148  0.47817696  0.37383338  0.40594204  0.41694249  0.34231438
   0.31207915  0.50198904]] Reward -28277.7254533 Loss 129164.351562
Episode 0 Step 1063 Action [[ 0.37805882  0.43802062  0.47705572  0.33859227  0.48055898  0.59234109
   0.46535217  0.46197896]] Reward -28305.9641542 Loss 11896.0058594
Episode 0 Step 1064 Action [[ 0.41040919  0.41746933  0.56809035  0.60198193  0.38009074  0.42242415
   0.36453323  0.48667623]] Reward -28329.2649942 Loss 183541.078125
Episode 0 Step 1065 Action [[ 0.5909828   0.6376751   0.70085757  0.38391945  0.59406394  0.36539617
   0.38060608  0.54671316]] Reward -28357.201685 Loss 60200.3867188
Episode 0 Step 1066 Action [[ 0.29858052  0.4227861   0.43765766  0.38128887  0.2668966   0.49278146
   0.29681937  0.41043301]] Reward -28379.9264229 Loss 68377.2734375
Episode 0 Step 1067 Action [[ 0.43429358  0.33219811  0.5424926   0.51039183  0.49619892  0.6072776
   0.38588078  0.31078649]] Reward -28408.2516627 Loss 210460.3125
Episode 0 Step 1068 Action [[ 0.53390201  0.44669501  0.37357831  0.33144828  0.35700264  0.38647106
   0.37452912  0.44325436]] Reward -28430.7151507 Loss 18297.7929688
Episode 0 Step 1069 Action [[ 0.42812196  0.30927725  0.47231682  0.33525606  0.18995197  0.54797723
   0.52492634  0.43209686]] Reward -28452.3777178 Loss 130556.625
Episode 0 Step 1070 Action [[ 0.44241685  0.2245892   0.24910492  0.28079935  0.46007997  0.38406715
   0.38666086  0.5072581 ]] Reward -28474.5730447 Loss 65547.125
Episode 0 Step 1071 Action [[ 0.40382903  0.5002337   0.46117453  0.52017976  0.30571312  0.35020175
   0.4736253   0.43356622]] Reward -28494.3990862 Loss 55068.078125
Episode 0 Step 1072 Action [[ 0.30271341  0.46075147  0.50744105  0.51655713  0.48983255  0.47062193
   0.48919292  0.41543304]] Reward -28520.2400047 Loss 176520.71875
Episode 0 Step 1073 Action [[ 0.51747672  0.49575275  0.41249684  0.60198969  0.45221911  0.43465862
   0.49942498  0.48485079]] Reward -28545.1997069 Loss 21023.9824219
Episode 0 Step 1074 Action [[ 0.35555385  0.35437838  0.46147607  0.52878143  0.5811431   0.58427882
   0.31561649  0.5075042 ]] Reward -28575.4657963 Loss 113933.28125
Episode 0 Step 1075 Action [[ 0.44189248  0.36707076  0.44621856  0.55366783  0.51595249  0.4407302
   0.69769517  0.35006919]] Reward -28602.3810323 Loss 70533.3125
Episode 0 Step 1076 Action [[ 0.5674795   0.57837596  0.389239    0.62431393  0.4952305   0.45316344
   0.47472103  0.38655615]] Reward -28629.8611575 Loss 81082.7578125
Episode 0 Step 1077 Action [[ 0.54014695  0.58789779  0.57669983  0.43636566  0.40588044  0.54344165
   0.55336879  0.27430962]] Reward -28658.4673886 Loss 75871.5
Episode 0 Step 1078 Action [[ 0.33492392  0.48682995  0.5219526   0.51328685  0.53558175  0.60605109
   0.56065034  0.37169301]] Reward -28689.3633392 Loss 27219.6523438
Episode 0 Step 1079 Action [[ 0.56837434  0.47949704  0.36455338  0.51809727  0.45641826  0.41768771
   0.42433553  0.45416006]] Reward -28715.20791 Loss 70181.71875
Episode 0 Step 1080 Action [[ 0.50588229  0.52800666  0.29553614  0.56873706  0.42361931  0.59844942
   0.26381087  0.47095428]] Reward -28743.5407365 Loss 29809.7382812
Episode 0 Step 1081 Action [[ 0.72119211  0.48594199  0.20579435  0.50501659  0.30679465  0.2699085
   0.57686836  0.48278545]] Reward -28764.1761661 Loss 71521.421875
Episode 0 Step 1082 Action [[ 0.30632799  0.43943956  0.50271367  0.48597739  0.53313663  0.37457492
   0.59769168  0.55641201]] Reward -28791.050918 Loss 84687.0234375
Episode 0 Step 1083 Action [[ 0.38714476  0.45976369  0.36709742  0.37927478  0.51992469  0.6280359
   0.29126822  0.35943503]] Reward -28821.5407296 Loss 24827.3222656
Episode 0 Step 1084 Action [[ 0.54982403  0.31771117  0.38502485  0.39162985  0.4614884   0.59592895
   0.4416659   0.38410245]] Reward -28849.4678827 Loss 89034.7265625
Episode 0 Step 1085 Action [[ 0.60685806  0.42416673  0.38244781  0.46096432  0.4418216   0.49424215
   0.54496516  0.45587491]] Reward -28875.2041376 Loss 171866.0625
Episode 0 Step 1086 Action [[ 0.43206303  0.5625923   0.42667376  0.62964755  0.50240604  0.25277127
   0.42637213  0.47791098]] Reward -28898.420079 Loss 4220.75
Episode 0 Step 1087 Action [[ 0.39747802  0.53206401  0.27167009  0.39571696  0.52800783  0.29959335
   0.63730259  0.3937075 ]] Reward -28923.2160518 Loss 90536.234375
Episode 0 Step 1088 Action [[ 0.49095319  0.62217364  0.41628454  0.48971653  0.45089552  0.46161997
   0.38847725  0.48308071]] Reward -28949.5799428 Loss 235.732574463
Episode 0 Step 1089 Action [[ 0.48313584  0.44877253  0.38940971  0.52517305  0.35164628  0.35544694
   0.64466529  0.3493371 ]] Reward -28971.9478474 Loss 64479.7460938
Episode 0 Step 1090 Action [[ 0.46863153  0.57697723  0.64501866  0.59986486  0.42898146  0.46550794
   0.3654374   0.49627553]] Reward -28998.8505904 Loss 9200.73339844
Episode 0 Step 1091 Action [[ 0.42971263  0.56234497  0.35384145  0.53804725  0.44357871  0.35396841
   0.32233812  0.37071114]] Reward -29023.7491158 Loss 73747.15625
Episode 0 Step 1092 Action [[ 0.45296867  0.36379804  0.43126744  0.54524406  0.42590517  0.39541965
   0.46699949  0.31328744]] Reward -29048.7896663 Loss 50552.8046875
Episode 0 Step 1093 Action [[ 0.37258836  0.37378104  0.62723894  0.5108082   0.47912722  0.38204654
   0.37171978  0.37332431]] Reward -29075.1921612 Loss 116989.40625
Episode 0 Step 1094 Action [[ 0.18524909  0.43971782  0.43920943  0.55251976  0.47068218  0.5571906
   0.35827198  0.66048941]] Reward -29103.9858228 Loss 2624.59155273
Episode 0 Step 1095 Action [[ 0.32140656  0.48438514  0.40940109  0.59603955  0.37021503  0.49362244
   0.42648717  0.39871084]] Reward -29130.1348356 Loss 68013.4765625
Episode 0 Step 1096 Action [[ 0.30090747  0.36846874  0.50513277  0.29194689  0.36385561  0.59352324
   0.30546629  0.58343913]] Reward -29158.142593 Loss 16320.5449219
Episode 0 Step 1097 Action [[ 0.41352915  0.52030929  0.4980364   0.32479898  0.54047105  0.36432487
   0.2291295   0.38988391]] Reward -29184.3574501 Loss 73200.4375
Episode 0 Step 1098 Action [[ 0.32975831  0.62571238  0.48925304  0.39503565  0.53347313  0.3573365
   0.28839625  0.56405353]] Reward -29209.8688902 Loss 31993.5371094
Episode 0 Step 1099 Action [[ 0.3746904   0.36395863  0.5420607   0.44528005  0.48531429  0.60638448
   0.48912292  0.32618468]] Reward -29238.0075661 Loss 97717.15625
Episode 0 Step 1100 Action [[ 0.51743661  0.38237792  0.52260491  0.50627103  0.41965162  0.29700393
   0.55475903  0.550945  ]] Reward -29259.8842585 Loss 221.849243164
Episode 0 Step 1101 Action [[ 0.59029225  0.37118646  0.52574799  0.36153465  0.33716781  0.52456318
   0.54485796  0.42851266]] Reward -29284.590441 Loss 72277.90625
Episode 0 Step 1102 Action [[ 0.54737364  0.49995124  0.47154136  0.4368222   0.45256861  0.43394734
   0.42292087  0.27824729]] Reward -29309.4854437 Loss 3092.49902344
Episode 0 Step 1103 Action [[ 0.37984036  0.51543514  0.44282175  0.35433078  0.48365749  0.54482479
   0.33931244  0.49624447]] Reward -29336.8374265 Loss 61219.9609375
Episode 0 Step 1104 Action [[ 0.52079247  0.46124243  0.52770665  0.32596056  0.45899759  0.33913375
   0.39449225  0.49459549]] Reward -29359.9694287 Loss 19468.4257812
Episode 0 Step 1105 Action [[ 0.33804189  0.50527818  0.55031051  0.51388108  0.36869866  0.44697837
   0.43124098  0.3986445 ]] Reward -29383.1918622 Loss 49551.390625
Episode 0 Step 1106 Action [[ 0.64920556  0.49598182  0.38470371  0.40794668  0.58188092  0.37019589
   0.51607365  0.52839106]] Reward -29408.8902918 Loss 81480.0
Episode 0 Step 1107 Action [[ 0.48078223  0.40729139  0.41395691  0.36693013  0.49289526  0.3240076
   0.4930325   0.19484166]] Reward -29432.0405201 Loss 22584.5117188
Episode 0 Step 1108 Action [[ 0.40801731  0.47590266  0.30373457  0.44711716  0.33736613  0.4241529
   0.55941712  0.52475617]] Reward -29453.8935991 Loss 81403.578125
Episode 0 Step 1109 Action [[ 0.44552589  0.41150065  0.53843445  0.36738097  0.46186465  0.4592621
   0.36074871  0.60500404]] Reward -29479.168989 Loss 18580.0429688
Episode 0 Step 1110 Action [[ 0.57510989  0.44083677  0.5100303   0.63674495  0.47721897  0.47015081
   0.57439145  0.42649796]] Reward -29504.6512902 Loss 71931.703125
Episode 0 Step 1111 Action [[ 0.42810289  0.39780971  0.52915422  0.38368879  0.39591489  0.64801197
   0.44075414  0.51061742]] Reward -29532.8900729 Loss 42537.6992188
Episode 0 Step 1112 Action [[ 0.50967626  0.50923597  0.37642877  0.47721611  0.4864088   0.3987799
   0.54100977  0.3949844 ]] Reward -29557.8684299 Loss 67270.0078125
Episode 0 Step 1113 Action [[ 0.52805841  0.46474142  0.29423817  0.37151784  0.50493386  0.60959065
   0.37232258  0.35321227]] Reward -29586.5508049 Loss 25485.3652344
Episode 0 Step 1114 Action [[ 0.6070513   0.40852186  0.39867817  0.40147655  0.50224664  0.39174749
   0.51622333  0.44956292]] Reward -29611.2113016 Loss 63740.9179688
Episode 0 Step 1115 Action [[ 0.26637477  0.44748275  0.26160637  0.54117212  0.48549139  0.3006072
   0.43084762  0.50102093]] Reward -29633.6036472 Loss 3795.34887695
Episode 0 Step 1116 Action [[ 0.52277576  0.37429003  0.5252982   0.46694978  0.45252043  0.62128143
   0.46467117  0.40044264]] Reward -29662.0358793 Loss 39078.9765625
Episode 0 Step 1117 Action [[ 0.53365814  0.33639334  0.5215611   0.39969964  0.30857426  0.48592177
   0.5419651   0.43631197]] Reward -29685.6420882 Loss 1176.73095703
Episode 0 Step 1118 Action [[ 0.38332985  0.39933328  0.55544835  0.55315817  0.34121548  0.49571017
   0.33202532  0.50756756]] Reward -29709.9483149 Loss 39989.9453125
Episode 0 Step 1119 Action [[ 0.55600677  0.37712324  0.37377653  0.44852147  0.43885737  0.47696281
   0.42848598  0.34400979]] Reward -29735.5625165 Loss 1297.80749512
Episode 0 Step 1120 Action [[ 0.38079087  0.51158183  0.54846219  0.47319839  0.40406     0.42085125
   0.60640388  0.45282562]] Reward -29760.4017842 Loss 39092.1445312
---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
<ipython-input-48-40a13eb2146d> in <module>()
    136 
    137 if __name__ == "__main__":
--> 138     simulate(train=1)

<ipython-input-48-40a13eb2146d> in simulate(train)
    105                 grads = critic.gradients(states, a_for_grad)
    106                 actor.train(states, grads)
--> 107                 actor.target_train()
    108                 critic.target_train()
    109 

<ipython-input-42-21f489758026> in target_train(self)
     31         for i in range(len(actor_weights)):
     32             actor_target_weights[i] = self.TAU * actor_weights[i] + (1 - self.TAU)* actor_target_weights[i]
---> 33         self.target_munet.set_weights(actor_target_weights)
     34 
     35     def actor_network(self, state_size,action_dim):

/home/daniel/Programs/anaconda/lib/python3.5/site-packages/keras/engine/topology.py in set_weights(self, weights)
   1971                 tuples.append((sw, w))
   1972             weights = weights[num_param:]
-> 1973         K.batch_set_value(tuples)
   1974 
   1975     @property

/home/daniel/Programs/anaconda/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in batch_set_value(tuples)
   2151             assign_ops.append(assign_op)
   2152             feed_dict[assign_placeholder] = value
-> 2153         get_session().run(assign_ops, feed_dict=feed_dict)
   2154 
   2155 

/home/daniel/Programs/anaconda/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in get_session()
    162     if not _MANUAL_VAR_INIT:
    163         with session.graph.as_default():
--> 164             _initialize_variables()
    165     return session
    166 

/home/daniel/Programs/anaconda/lib/python3.5/site-packages/keras/backend/tensorflow_backend.py in _initialize_variables()
    330     uninitialized_variables = []
    331     for v in variables:
--> 332         if not hasattr(v, '_keras_initialized') or not v._keras_initialized:
    333             uninitialized_variables.append(v)
    334             v._keras_initialized = True

KeyboardInterrupt: 

In [4]:
%matplotlib
f = plt.figure(figsize=(14,8))
Hs = 2400
A1 = 0.004
mu1 = 250 
sigma1 = 50
A2 = 0.004
mu2 = 250
sigma2 = 50
dt = 1
state_dim = 10
x = np.arange(Hs)
d = np.zeros((2,Hs))
d[0,:] = A1*np.exp((-1*(x-mu1)**2)/(2*sigma1**2))
d[1,:] = A2*np.exp((-1*(x-mu2)**2)/(2*sigma2**2))
vref = np.zeros((state_dim,))
env  = linear_env.env(1,d,np.zeros((10,)))
hist_v,hist_f,hist_u = env.free_sim()
plt.plot(x,np.transpose(np.divide(hist_v,np.transpose(np.matlib.repmat(env.vmax,Hs,1)))))


Using matplotlib backend: Qt5Agg
Simulation time set to the perturbation time: 2400 [1 s]
Out[4]:
[<matplotlib.lines.Line2D at 0x7feea81596d8>,
 <matplotlib.lines.Line2D at 0x7feea81598d0>,
 <matplotlib.lines.Line2D at 0x7feea8159ac8>,
 <matplotlib.lines.Line2D at 0x7feea8159cc0>,
 <matplotlib.lines.Line2D at 0x7feea8159eb8>,
 <matplotlib.lines.Line2D at 0x7feea815f0f0>,
 <matplotlib.lines.Line2D at 0x7feea815f2e8>,
 <matplotlib.lines.Line2D at 0x7feea815f4e0>,
 <matplotlib.lines.Line2D at 0x7feea815f6d8>,
 <matplotlib.lines.Line2D at 0x7feea815f8d0>]

In [9]:
np.linalg.norm([2,4],ord=2)


Out[9]:
4.4721359549995796

In [12]:
np.linalg.norm([2,4],ord=2)


Out[12]:
4.4721359549995796

In [35]:
x  = np.arange(1000)
yvals = []
m = [0,1,2,3,4]
for mv in m:
    yvals.append(mv*x)

lines = plt.plot(x,np.transpose(np.array(yvals)))
plt.legend(lines,list(map(lambda x: "v"+str(x+1),range(5))),loc='best')
plt.show()

In [19]:
np.arange(5)


Out[19]:
array([0, 1, 2, 3, 4])

In [27]:
np.shape(np.array(yvals))


Out[27]:
(5, 1000)

In [ ]: