sbx

sbx copied to clipboard

[Bug] TQC Hyperparameter optimization: Results do not match the reference. This is likely a bug/unexpected loss of precision.

2

### 🐛 Bug Hi, When I try to run TQC hyperparameter optimization with multiple jobs (n-jobs>1) with a GPU (this also happens with multiple CPU cores and n-jobs=1), it gives...

edmund735

[Feature Request] Recurrent policies

16

There are recurrent (LSTM) policy options for sb3 (e.g. [RecurrentPPO](https://github.com/Stable-Baselines-Team/stable-baselines3-contrib/blob/master/sb3_contrib/ppo_recurrent/ppo_recurrent.py)). It would be great to have recurrent PPO implemented for sbx.

jamesheald

[Question] `MultiInputPolicy` not supported (DroQ)

1

Hey, I'm trying to use SBX, specifically `DroQ`, with `MultiInputPolicy`. I get the error: ``` ValueError: Policy MultiInputPolicy unknown ``` Why is that? I thought SBX is compatible with SB3.

jbirnick

## Description Including state representation into SAC, following https://github.com/sfujim/TD7. Note: many tricks missing and using smooth update. ## Motivation and Context - [ ] I have raised an issue to...

araffin

Implements the [feature extractors](https://github.com/DLR-RM/stable-baselines3/blob/master/stable_baselines3/common/torch_layers.py) from SB3 in JAX ## Description ## Motivation and Context Achieving feature parity with SB3 - [x] I have raised an issue to propose this change...

joaogui1

Adding Feature Extractors

6

I think adding the [feature extractors](https://github.com/DLR-RM/stable-baselines3/blob/master/stable_baselines3/common/torch_layers.py) from SB3 is a good next step towards feature parity between the libraries

joaogui1

## Description ## 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 changes -...

araffin

[Feature Request] Dict Obs Spaces Support

2

### 🚀 Feature As far as I understood by some preliminar tests, SBX currently does not support Dict observation spaces, do you have this feature in your roadmap? If yes...

alexpalms

[Question] framestack and train_freq for sbx

2

Hi there! Thank you for developing SBX! I'm currently working with SB3 for real-time robot control and was wondering if SBX supports the `framestack` using `DummyVecEnv` wrapper? Additionally, can SBX...

Jackflyingzzz

## Description ## 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 changes -...

araffin