Antonin RAFFIN

Hello, could you do a PR to fix this issue?

Hello, > I just wanted to make sure that I'm not missing something. Is this the right way to do it? You should also save the replay buffer (see doc...

Duplicate of https://github.com/DLR-RM/stable-baselines3/issues/36 https://github.com/DLR-RM/stable-baselines3/issues/802 and https://github.com/DLR-RM/stable-baselines3/issues/712 PS: could you do a PR that a note about that in our doc?

what mujoco version do you use? SB3 is only fully compatible with 0.29.1 for now. Do you have the same issue with built-env mujoco env? (for instance `HalfCheetah-v4`) I haven't...

I'm doing many runs on MuJoCo envs and I cannot see the effect you describe so far: https://wandb.ai/openrlbenchmark/sbx/runs/99wrpkc7?nw=nwuseraraffin (other runs are available in https://wandb.ai/openrlbenchmark/sbx/). To reproduce, use the train script...

Note: when using multiple envs, you should probably adjust the `n_steps` to have a constant batch size For instance: ``` JAX_PLATFORMS=cpu CUDA_VISIBLE_DEVICES= python train.py --algo ppo \ --env HalfCheetah-v4 -P...

https://github.com/DLR-RM/stable-baselines3/pull/1837#issuecomment-2402932624

Support added in SB3 v2.4.0a11 (pre-release, also on master), please give it a try.

> Can stable-baselines3 be installed through pip without cuda dependencies? You need to install torch cpu version first: https://github.com/DLR-RM/stable-baselines3/blob/56c153f048f1035f239b77d1569b240ace83c130/.github/workflows/ci.yml#L34-L35

Hello, this is hard to answer if you don't provide a minimal example to reproduce the behavior. `.learn()` does two things (see docs): collect data and train the model (when...