In [1]:

    

from MonteCarloControl import MonteCarloControl
import pickle
from TDControl import Sarsa
from Utility import Plot2D
import numpy as np


    

In [2]:

    

mc = MonteCarloControl()
mc.solve(10000000, 100)
with open("q_star_100.obj", 'wb') as output:
    pickle.dump(mc.q, output)


    

In [3]:

    

with open("q_star_100.obj", 'rb') as output:
    q_star = pickle.load(output)
sarsa = Sarsa(q_star)
lambda_mse = []
for n_lambda in np.arange(0, 1.1, 0.1):
    lambda_mse.append(sarsa.solve(n_lambda))


    

In [4]:

    

Plot2D(np.arange(0, 1.1, 0.1), lambda_mse)


    

In [5]:

    

mse = sarsa.solve(0, need_list=True)


    

In [6]:

    

Plot2D(range(1000), mse)


    

In [7]:

    

mse = sarsa.solve(1, need_list=True)


    

In [8]:

    

Plot2D(range(1000), mse)


    

In [ ]: