In [26]:

    

import gym
env = gym.make('FrozenLake-v0')
policy=[0,2,1,0,
        0,0,1,0,
        2,2,1,0,
        0,2,2,0]
sum_reward=0
for episode in range(100):
    obs=env.reset()
    done=False
    #print("episode: {}".format(episode))
    while not done:
        obs,reward,done,info=env.step(policy[obs])
    sum_reward+=reward
    #env.render()
print(sum_reward)


    

    




[2017-09-23 12:10:56,456] Making new env: FrozenLake-v0






    




15.0

In [ ]: