In [1]:

    

import numpy as np
import sys
if "../" not in sys.path:
  sys.path.append("../")

from envs.gridworld import GridworldEnv
from policy_evaluation import policy_eval

# for auto-reloading external modules
# see http://stackoverflow.com/questions/1907993/autoreload-of-modules-in-ipython
%load_ext autoreload
%autoreload 2


    

In [2]:

    

env = GridworldEnv()


    

In [3]:

    

random_policy = np.ones([env.nS, env.nA]) / env.nA
v = policy_eval(random_policy, env)


    

In [4]:

    

# Test: Make sure the evaluated policy is what we expected
expected_v = np.array([0, -14, -20, -22, -14, -18, -20, -20, -20, -20, -18, -14, -22, -20, -14, 0])
np.testing.assert_array_almost_equal(v, expected_v, decimal=2)