NotImplementedError

[ashing-zhang]

Traceback (most recent call last): File "D:\Master\Codes\pytorch-ddpg\main.py", line 156, in train(args.train_iter, agent, env, evaluate, File "D:\Master\Codes\pytorch-ddpg\main.py", line 44, in train observation2, reward, done, info = env.step(action) File "D:\AI\Software\Conda\Miniconda\envs\torch\lib\site-packages\gym\core.py", line 349, in step return self.env.step(self.action(action)) File "D:\AI\Software\Conda\Miniconda\envs\torch\lib\site-packages\gym\core.py", line 353, in action raise NotImplementedError NotImplementedError

[fuhaiwang]

You can change the code line#126 in main.py: from env = NormalizedEnv(gym.make(args.env)) to env = gym.make(args.env)

Or you can do: change the code line#8 and line#13 in normalized_env.py: from def _action(self, action): and def _reverse_action(self, action): to def action(self, action): and def reverse_action(self, action):

Because the gym is updated (Maybe?). The function in class NormalizedEnv should delete "_". You can see the father class ActionWrapper in https://github.com/openai/gym/blob/master/gym/core.py

That's all!

[ashing-zhang]

Thank you sir.

---Original--- From: @.> Date: Fri, Nov 26, 2021 17:45 PM To: @.>; Cc: @.@.>; Subject: Re: [ghliu/pytorch-ddpg] NotImplementedError (Issue #13)

You can change the code line#126 in main.py: from env = NormalizedEnv(gym.make(args.env)) to env = gym.make(args.env)

Or you can do: change the code line#8 and line#13 in normalized_env.py: from def _action(self, action): and def _reverse_action(self, action): to def action(self, action): and def reverse_action(self, action):

Because the gym is updated (Maybe?). The function in class NormalizedEnv should delete "_". You can see the father class ActionWrapper in https://github.com/openai/gym/blob/master/gym/core.py

That's all!

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub, or unsubscribe. Triage notifications on the go with GitHub Mobile for iOS or Android.