Antonin RAFFIN

>i cannot reproduce the work of other publications as most of the literature does exactly that. TD3 is nice, but using an different algorithm is less comparable. TD3 is literally...

Re-opening as it might be helpful to be able to tune `qf_learning_rate` as done in https://github.com/araffin/sbx. We need to see how much complexity it adds though.

> can I not do this because they share the optimizer? yes > If so, can I change the optimizer so they can or would you not recommend this? you...

> Is this feature request still under consideration yes, but help from contributors is needed. Otherwise, you can have a look at SBX: https://github.com/araffin/sbx > Is this the only difference...

@timothe-chaumont as you did the implementation in https://github.com/DLR-RM/stable-baselines3/pull/984, could you have a look? > `new_logger.dump()` I would expect `dump(num_timesteps)` there

Hello, there is an important information missing which is your network architecture. The rollout buffer store things in the RAM not on the GPU. And most GPU memory is taken...

This should answer your question: https://github.com/DLR-RM/stable-baselines3/blob/aab545901fe331814f822060d677f22191cba419/stable_baselines3/common/buffers.py#L391-L398

https://github.com/DLR-RM/stable-baselines3/pull/1720#issuecomment-1776700957

> the number of used environments improves the GPU usage? are you using subprocesses? if so, that might be due to the way python multiprocessing work. > This should mean...

> Thanks @araffin ! Out of curiosity, may I ask why the switch between torch and numpy for the backend? to be consistent with the rest of the buffers and...