[RL學習篇][#2] 簡單的grid_mdp測試程式

 

下方是用來簡單的測試 grid_mdp.py的程式，執行後會用隨機動作去跑動作。

 

import gym
import tensorflow
import random
from gym import wrappers

env = gym.make('GridWorld-v0')

env = wrappers.Monitor(env, './outputs/grid_mdp-experiment-', force=True)

for episode in range(100):
    env.reset()
    for i in range(100):
        env.render()
        next_state, reward, done, _ = env.step(random.choice(env.action_space)) # take a random action

        if done :
            break

    print('episdoe: ', episode)

wrappers.Monitor.close(env)

 

 ========================修正事項====================

2018.05.18:  執行上方程式有時出現以下錯誤訊息

　　Traceback (most recent call last):
　　File "/home/lsa-dla/PycharmProjects/grid_mdp/lsa_test1.py", line 11, in <module>
　　env.reset()
　　File "/home/lsa-dla/gym/gym/wrappers/monitor.py", line 37, in reset
　　self._before_reset()
　　File "/home/lsa-dla/gym/gym/wrappers/monitor.py", line 185, in _before_reset
　　self.stats_recorder.before_reset()
　　File "/home/lsa-dla/gym/gym/wrappers/monitoring/stats_recorder.py", line 68, in before_reset
　　raise error.Error("Tried to reset environment which is not done. While the monitor is active for {}, you cannot call reset() unless the episode is over.".format(self.env_id))
　　gym.error.Error: Tried to reset environment which is not done. While the monitor is active for GridWorld-v0, you cannot call reset() unless the episode is over.
　　Exception ignored in: <bound method Viewer.__del__ of <gym.envs.classic_control.rendering.Viewer object at 0x7f1ed7e63208>>

修正方式將 

　　for episode in range(100):

改成

   　　 while True:

即可正常執行

---------------------------------------------------------------------------