Antonin RAFFIN

Hello, > Passed from SubprocVecEnv to DummyVecEnv as the former raises an Error Can you elaborate on that? I think the only change that makes sense here is to switch...

Related: https://github.com/DLR-RM/stable-baselines3/issues/219#issuecomment-1075868593 > it should be supported for the environment spaces. Would you volunteer to add support for it? > Alternatives After a quick github search, there is actually some...

How do you define the value?

Still, what is the definition of the value? if you manage to answer that question, you should be able to answer yours.

> Regarding the error : this is what I get when I run the code hmm, might be related to mac os. I cannot reproduce the issue locally and I...

> I think the value is the output of the value network when giving the current observation. What does it relate to my question? Yes, but this is a bit...

> This difference depends on the reward scale. Thus, the clipping depends on the reward scale. Am I right? exactly =) > actually pose this issue because I don't understand...

Hello, the original code comes from https://github.com/openai/baselines/commit/bb403781182c6e31d3bf5de16f42b0cb0d8421f7#diff-e3578f89a8370e447f38686c0121044f4ba262b016085e8da4c981fbd784515c (by @joschu) > So both work_remote and remote use close()? How can we use pipe to communicate later? Does it indeed need here?...

> is the flag passed to render or to init? this won't break with gym 0.26, right? I would go for a flag passed to the render method as it...

Hello, could you give some pointer/example on how to integrate that extension? will you be willing to contribute such extension?