Timo Klein

WIP: SAC-discrete implementation

5

## Description Adds the SAC-discrete algorithm as discussed in https://github.com/vwxyzjn/cleanrl/issues/266. ## Types of changes - [ ] Bug fix - [ ] New feature - [x] New algorithm - [...

SAC discrete

2

Hey there! I've used this repo's SAC code as starting point for an implementation of SAC-discrete ([paper](https://arxiv.org/pdf/1910.07207.pdf)) for a project of mine. If you're interested, I'd be willing to contribute...

Type hints

1

## Description As discussed on Discord, I've done basic type hints for PPO and DQN. Everything checks out with mypy 0.982 (`mypy cleanrl/ppo.py --show-error-codes --ignore-missing-imports`). Of course we can have...

## Problem When trying to install the package, it will fail with a variety of issues related to **mujoco-py**, e.g. `error: legacy-install-failure` or `You appear to be missing MuJoCo. We...

Doesn't work on Python 3.12 or 3.11

9

As per `pyproject.toml`, this package should work for Python versions >=3.8. However, it actually only works up to and including Python version 3.10. For higher Python versions it throws `ValueError:...

Fix Array defaults for struct.PyTreeNode

1

I've been working some on this and made a little progress at least: I'm fetching the default values for all jax.Arrays and setting a field with `default_factory= lambda: default`. The...