vwxyzjn / cleanrl

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
http://docs.cleanrl.dev
Other
4.91k stars 566 forks source link

Add support for python 3.10 (and remove pybullet) #386

Closed pseudo-rnd-thoughts closed 1 year ago

pseudo-rnd-thoughts commented 1 year ago

Description

CleanRL has been limited to <3.10 due to PyBullet and IssacGym. Due to updating to Gymnasium which includes Mujoco-v4 elevating the need for PyBullet as Mujoco is now freely available. This PR provides support for python 3.10 and removes PyBullet.

This should have no impact on the performance of algorithms.

Types of changes

Checklist:

If you need to run benchmark experiments for a performance-impacting changes:

vercel[bot] commented 1 year ago

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
cleanrl ✅ Ready (Inspect) Visit Preview 💬 Add feedback May 13, 2023 9:44am
pseudo-rnd-thoughts commented 1 year ago

@vwxyzjn I have tested installed the PettingZoo group locally with no issue and checking the pypi of Tinyscaler (https://pypi.org/project/tinyscaler/), I can't see any issues. Any ideas?

vwxyzjn commented 1 year ago

@vwxyzjn I have tested installed the PettingZoo group locally with no issue and checking the pypi of Tinyscaler (https://pypi.org/project/tinyscaler/), I can't see any issues. Any ideas?

Probably because tinyscalar does have Mac wheels https://pypi.org/project/tinyscaler/1.2.5/#files. If this is a problem, feel free to remove the pettingzoo Mac CI.