Quentin Gallouédec

Multiprocessing support for HerReplayBuffer

30

## Description Make `HerReplayBuffer` compatible with Multiprocessing. ## Motivation and Context - [ ] I have raised an issue to propose this change ([required](https://github.com/DLR-RM/stable-baselines3/blob/master/CONTRIBUTING.md) for new features and bug fixes)...

panda-gym v2

6

## Description Update benchmark for latest version of panda-gym. ## Motivation and Context - [ ] I have raised an issue to propose this change ([required](https://github.com/DLR-RM/stable-baselines3/blob/master/CONTRIBUTING.md) for new features and...

Multiple models for optimization

4

## Description ## Motivation and Context - [x] I have raised an issue to propose this change ([required](https://github.com/DLR-RM/stable-baselines3/blob/master/CONTRIBUTING.md) for new features and bug fixes) #204 closes #204 ## Types of...

See https://github.com/DLR-RM/rl-baselines3-zoo/pull/244

`Self` type support

1

It would be nice to support the `Self` type in the future. Is there a plan in this direction? [PEP 673](https://peps.python.org/pep-0673/) ## Code example `foo.py`: ```python from typing_extensions import Self...

Small issue: ```shell $ python -m cleanrl_utils.reproduce --run openrlbenchmark/cleanrl/runs/c1y1qnz4 # run the following python3 -m venv venv source venv/bin/activate pip install -r https://api.wandb.ai/files/openrlbenchmark/cleanrl/c1y1qnz4/requirements.txt curl -OL https://api.wandb.ai/files/openrlbenchmark/cleanrl/c1y1qnz4/code/cleanrl/ppo_atari.py python /fsx/costa/cleanrl/cleanrl/ppo_atari.py --track --env-id...

## Description After https://github.com/DLR-RM/rl-baselines3-zoo/pull/355#issuecomment-1425749593 ## Motivation and Context - [ ] I have raised an issue to propose this change ([required](https://github.com/DLR-RM/stable-baselines3/blob/master/CONTRIBUTING.md) for new features and bug fixes) ## Types of...

gSDE noise sampling with TQC can raise ValueError due to nan in `log_std`

1

## Description In some rare cases, (encountered once) noise sampling in gSDE can break. It happened once with TQC on HalfCheetahBulletEnv-v0, after 800k timesteps. For some reason, the entropy loss...

SIL

8

[Self Imitation Learning](https://arxiv.org/abs/1806.05635) @emrul has implemented SAIL, see https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/pull/139#issuecomment-1445114579 @emrul, is there an official implementation for those two? Do you match the results from the paper with your implementation?

IQN

4

## Description ## Context - [ ] I have raised an issue to propose this change ([required](https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/blob/master/CONTRIBUTING.md)) ## Types of changes - [ ] Bug fix (non-breaking change which fixes...