Antonin RAFFIN

> I just want to find an example program of LSTM feature extractor. You can take a look at SB3 code for that: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/blob/master/sb3_contrib/common/recurrent/policies.py#L22 Disclaimer: using LSTM with RL is...

@qgallouedec could you test this PR (do `make pytest`) on a MPS enabled machine? (best would be to test sb3 contrib too) We should probably add a warning in the...

Thanks for testing =)

Hello, > do we have an option to anneal /schedule action noises for continuous environments? out of the box no, but you can define a schedule for it, for instance,...

> Maybe we could adapt the code to accept callables so that the lin_0.1 syntax would work ? You mean `lin_0.1` in the RL Zoo? > You could also use...

> as callable instead of scalar value it could directly be a schedule in the zoo, isn't it? Is it what you propose? not really, I would rather define a...

Hello, please fill up the custom gym env template.

> I updated it will a link to the custom gym environment because it's too long to paste it here. Please take a close look at the custom env issue...

> One thing that confuses me is, what mechanism enables the update phase to indefinitely eat up memory? You mean there is a memory leak? Does it happen with less...

Hello, you can find a working proof of concept here: https://github.com/DLR-RM/rl-baselines3-zoo/blob/87001ed8a40f817d46c950e283d1ca29e405ad71/utils/callbacks.py#L95 (it is not polished but it works)