Antonin RAFFIN
Antonin RAFFIN
> In practice, I guess your way could work, but in principle, the representation ability is supposed to be part of the agent's functionality instead of properties of the (wrapped)...
Duplicate of https://github.com/DLR-RM/stable-baselines3/issues/1712 I would appreciate a PR that updates the documentation ;)
> Is there a proper way to do so using SB3? You should have a look at gym wrappers/VecEnv wrapper (we have tutorials/examples in our doc).
Hello, thanks for reporting the issue, I think we need to give access to the common parent when using a `CallbackList`.
> Is there really no work around? a quick workaround is to redefine `StopTrainingOnRewardThreshold`, combine the two callbacks in one a better workaround is to fix the code and I...
Hello, thanks for reporting the bug =) I would happy to receive a PR that fixes this issue. We also need to document the behavior, because we need to decide...
Hello, what have you tried so far (see also links in our doc, please provide minimal and working code) and what is the current issue?
could you please give the full traceback ?
Hmm, it's weird that the wrapper is deriving from both gym Wrapper and SB3 VecEnv and I guess that's the issue. See https://github.com/Farama-Foundation/Gymnasium/blob/2f19f3ed69b9423444ec6f7cfa46c5fb079168c5/gymnasium/core.py#L440-L443 So if you only derive from `VecEnv`...
Remove `gym.Wrapper` and `gym.Wrapper.__init__(self, env)`