[RL學習篇][#2] 簡單的grid_mdp測試程式

 1 import gym
 2 import tensorflow
 3 import random
 4 from gym import wrappers
 5 
 6 env = gym.make(‘GridWorld-v0‘)
 7 
 8 env = wrappers.Monitor(env, ‘./outputs/grid_mdp-experiment-‘, force=True)
 9 
10 for episode in range(100):
11     env.reset()
12     for i in range(100):
13         env.render()
14         next_state, reward, done, _ = env.step(random.choice(env.action_space)) # take a random action
15 
16         if done :
17             break
18 
19     print(‘episdoe: ‘, episode)
20 
21 wrappers.Monitor.close(env)