In [1]:
from own_hyperparameter_tuner import *


[2016-07-24 10:53:37,209] Site environment registry incorrect: Scoreboard did not register all envs: set(['AcrobotContinuous-v0'])

In [2]:
lr_list = np.linspace(1e-5, 1e-2, num=10)
lr_list = zip(lr_list * 0.1, lr_list)  # the order is actor_lr critic_lr, the critic needs to be faster
print('Using the following parameter sets: ')
print('lr_list: ', lr_list)

noise_levels = np.linspace(start= 0.5, stop=1, num = 5)
print('noise levels: ', noise_levels)

ql2_factor = np.linspace(start= 0, stop=0.01, num = 2)
print('weight decay ql2:', ql2_factor)

paramdict = { 'env':['InvertedPendulum-v1'],
              'lr': lr_list,
              'noise_level': noise_levels,
              'weight_decay': ql2_factor}

hpt = hyper_parameter_tuner(param_dict= paramdict, num_exp= 1000, dataname= 'hypertest')
hpt.run_experiments()


Using the following parameter sets: 
('lr_list: ', [(1.0000000000000002e-06, 1.0000000000000001e-05), (0.00011200000000000001, 0.0011200000000000001), (0.00022300000000000003, 0.0022300000000000002), (0.0003340000000000001, 0.0033400000000000005), (0.00044500000000000003, 0.00445), (0.00055599999999999996, 0.0055599999999999998), (0.00066700000000000006, 0.0066700000000000006), (0.00077800000000000005, 0.0077800000000000005), (0.00088900000000000003, 0.0088900000000000003), (0.001, 0.01)])
('noise levels: ', array([ 0.5  ,  0.625,  0.75 ,  0.875,  1.   ]))
('weight decay ql2:', array([ 0.  ,  0.01]))
starting experiments...
##################################################
starting run  0
using values
{'weight_decay': 0.0, 'lr': (0.00022300000000000003, 0.0022300000000000002), 'env': 'InvertedPendulum-v1', 'noise_level': 1.0}
[2016-07-24 10:53:37,483] Making new env: InvertedPendulum-v1
state dim 4
action dim 1
[2016-07-24 10:53:41,209] Action '-0.0849156679597' is not contained within action space 'Box(1,)'.
result after minibatch no. 0 : mean squared error: 1.0
result after minibatch no. 1000 : mean squared error: 0.0534619577229
result after minibatch no. 2000 : mean squared error: 0.763199329376
result after minibatch no. 3000 : mean squared error: 1.57707619667
result after minibatch no. 4000 : mean squared error: 2.5402636528
result after minibatch no. 5000 : mean squared error: 3.91431951523
result after minibatch no. 6000 : mean squared error: 3.12555813789
result after minibatch no. 7000 : mean squared error: 6.19874286652
result after minibatch no. 8000 : mean squared error: 4.84627151489
result after minibatch no. 9000 : mean squared error: 3.78626871109
sorted test lengths [2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 4.0, 19.0, 19.0, 19.0, 19.0, 19.0, 19.0, 19.0, 20.0, 20.0, 20.0, 20.0, 20.0, 20.0, 20.0, 20.0, 20.0, 20.0, 20.0, 20.0, 20.0, 21.0, 21.0, 21.0, 21.0, 21.0, 21.0, 21.0, 21.0, 21.0, 21.0, 22.0, 22.0, 22.0, 22.0, 22.0, 22.0, 22.0, 22.0, 22.0, 23.0, 23.0, 23.0, 23.0, 23.0, 23.0, 24.0, 24.0, 24.0, 24.0, 25.0, 25.0, 25.0, 25.0, 26.0, 26.0, 26.0, 26.0, 26.0, 27.0, 28.0, 28.0, 28.0, 29.0, 29.0, 29.0, 30.0, 30.0, 30.0, 30.0, 31.0, 31.0, 32.0, 33.0, 34.0, 35.0]
closing the interactive session
deling <ddpg3.ddpg instance at 0x7f161afbd320>
score:  24.3333333333
[2016-07-24 11:01:07,621] Making new env: InvertedPendulum-v1
##################################################
starting run  1
using values
{'weight_decay': 0.01, 'lr': (0.001, 0.01), 'env': 'InvertedPendulum-v1', 'noise_level': 1.0}
state dim 4
action dim 1
[2016-07-24 11:01:08,999] Action '-0.0572208238214' is not contained within action space 'Box(1,)'.
result after minibatch no. 0 : mean squared error: 478.603912354
result after minibatch no. 1000 : mean squared error: 23.9796695709
result after minibatch no. 2000 : mean squared error: 5.90059518814
result after minibatch no. 3000 : mean squared error: 3.81873250008
result after minibatch no. 4000 : mean squared error: 2.731133461
result after minibatch no. 5000 : mean squared error: 3.45205116272
result after minibatch no. 6000 : mean squared error: 1.58090257645
result after minibatch no. 7000 : mean squared error: 2.52751135826
result after minibatch no. 8000 : mean squared error: 2.36416101456
result after minibatch no. 9000 : mean squared error: 2.1449906826
sorted test lengths [2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 2.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 3.0, 5.0, 18.0, 19.0, 19.0, 19.0, 19.0, 19.0, 19.0, 19.0, 20.0, 20.0, 20.0, 20.0, 20.0, 20.0, 21.0, 21.0, 21.0, 21.0, 21.0, 21.0, 21.0, 21.0, 22.0, 22.0, 22.0, 22.0, 22.0, 23.0, 23.0, 23.0, 23.0, 23.0, 23.0, 23.0, 24.0, 24.0, 24.0, 24.0, 24.0, 24.0, 24.0, 24.0, 24.0, 25.0, 25.0, 25.0, 26.0, 26.0, 26.0, 26.0, 26.0, 26.0, 27.0, 27.0, 27.0, 27.0, 28.0, 28.0, 28.0, 29.0, 30.0, 30.0, 30.0, 30.0, 30.0, 31.0, 31.0, 31.0, 32.0, 33.0, 33.0, 35.0, 36.0, 37.0]
closing the interactive session
deling <ddpg3.ddpg instance at 0x7f159884f2d8>
score:  25.3939393939
[2016-07-24 11:08:17,034] Making new env: InvertedPendulum-v1
##################################################
starting run  2
using values
{'weight_decay': 0.0, 'lr': (1.0000000000000002e-06, 1.0000000000000001e-05), 'env': 'InvertedPendulum-v1', 'noise_level': 1.0}
state dim 4
action dim 1
[2016-07-24 11:08:18,426] Action '-0.374199877511' is not contained within action space 'Box(1,)'.
result after minibatch no. 0 : mean squared error: 1.0
result after minibatch no. 1000 : mean squared error: 1.19482409954
result after minibatch no. 2000 : mean squared error: 6.00719261169
result after minibatch no. 3000 : mean squared error: 12.7374343872
closing the interactive session
---------------------------------------------------------------------------
KeyboardInterrupt                         Traceback (most recent call last)
<ipython-input-2-cb6db2fe23d4> in <module>()
     16 
     17 hpt = hyper_parameter_tuner(param_dict= paramdict, num_exp= 1000, dataname= 'hypertest')
---> 18 hpt.run_experiments()

/home/ga56muj/Documents/DeepRL/dpg/own_hyperparameter_tuner.py in run_experiments(self)
     43             print('using values')
     44             print(value_dict)
---> 45             score = self.run_trial(value_dict=value_dict)
     46             print('score: ', score)
     47             score_params_list.append((score, value_dict))

/home/ga56muj/Documents/DeepRL/dpg/own_hyperparameter_tuner.py in run_trial(self, value_dict)
     65                         ) as ddpg3_instance:
     66 
---> 67             score = ddpg3_instance.main()
     68 
     69         return score

/home/ga56muj/Documents/DeepRL/dpg/ddpg3.py in main(self)
    467 
    468         self.initialize_training(self.sess)
--> 469         return self.start_training()
    470 
    471     def plot_replay_memory_2d_state_histogramm(self):

/home/ga56muj/Documents/DeepRL/dpg/ddpg3.py in start_training(self, dataname, save)
    168 
    169             # run episode
--> 170             episode_length = self.run_episode(test_run= False, enable_render=False, limit= 10000)
    171 
    172             self.train_lengths.append(episode_length)

/home/ga56muj/Documents/DeepRL/dpg/ddpg3.py in run_episode(self, enable_render, limit, test_run)
    134                 action_raw = self.eval_mu(state)
    135             else:
--> 136                 action_raw = self.eval_mu(state) + self.ou_process.ou_step()*self.noise_scale
    137 
    138             action = self.rescale_action(action_raw)

/home/ga56muj/Documents/DeepRL/dpg/ddpg3.py in eval_mu(self, state)
    437 
    438     def eval_mu(self, state):
--> 439         return self.mu.eval(feed_dict= {self.state_raw : state})
    440 
    441     def eval_q(self, state, action):

/home/ga56muj/Documents/deeprl-python/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.pyc in eval(self, feed_dict, session)
    500 
    501     """
--> 502     return _eval_using_default_session(self, feed_dict, self.graph, session)
    503 
    504 

/home/ga56muj/Documents/deeprl-python/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.pyc in _eval_using_default_session(tensors, feed_dict, graph, session)
   3332                        "the tensor's graph is different from the session's "
   3333                        "graph.")
-> 3334   return session.run(tensors, feed_dict)
   3335 
   3336 

/home/ga56muj/Documents/deeprl-python/local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in run(self, fetches, feed_dict, options, run_metadata)
    338     try:
    339       result = self._run(None, fetches, feed_dict, options_ptr,
--> 340                          run_metadata_ptr)
    341       if run_metadata:
    342         proto_data = tf_session.TF_GetBuffer(run_metadata_ptr)

/home/ga56muj/Documents/deeprl-python/local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run(self, handle, fetches, feed_dict, options, run_metadata)
    562     try:
    563       results = self._do_run(handle, target_list, unique_fetches,
--> 564                              feed_dict_string, options, run_metadata)
    565     finally:
    566       # The movers are no longer used. Delete them.

/home/ga56muj/Documents/deeprl-python/local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_run(self, handle, target_list, fetch_list, feed_dict, options, run_metadata)
    635     if handle is None:
    636       return self._do_call(_run_fn, self._session, feed_dict, fetch_list,
--> 637                            target_list, options, run_metadata)
    638     else:
    639       return self._do_call(_prun_fn, self._session, handle, feed_dict,

/home/ga56muj/Documents/deeprl-python/local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _do_call(self, fn, *args)
    642   def _do_call(self, fn, *args):
    643     try:
--> 644       return fn(*args)
    645     except tf_session.StatusNotOK as e:
    646       error_message = compat.as_text(e.error_message)

/home/ga56muj/Documents/deeprl-python/local/lib/python2.7/site-packages/tensorflow/python/client/session.pyc in _run_fn(session, feed_dict, fetch_list, target_list, options, run_metadata)
    626       else:
    627         return tf_session.TF_Run(
--> 628             session, None, feed_dict, fetch_list, target_list, None)
    629 
    630     def _prun_fn(session, handle, feed_dict, fetch_list):

KeyboardInterrupt: 

In [ ]: