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
5.54k stars 631 forks source link

TD3 jax fix #285

Closed joaogui1 closed 2 years ago

joaogui1 commented 2 years ago

Description

JAX version of #281

Types of changes

Checklist:

If you are adding new algorithms or your change could result in performance difference, you may need to (re-)run tracked experiments. See https://github.com/vwxyzjn/cleanrl/pull/137 as an example PR.

vercel[bot] commented 2 years ago

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

Name Status Preview Updated
cleanrl ✅ Ready (Inspect) Visit Preview Oct 20, 2022 at 9:34PM (UTC)
vwxyzjn commented 2 years ago

Find no sign of regression

image image image

Regression report: https://wandb.ai/openrlbenchmark/cleanrl-cache/reports/-285-MuJoCo-CleanRL-s-TD3-JAX--VmlldzoyODI2ODIy

vwxyzjn commented 2 years ago

Thanks @joaogui1!