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

JAX TD3 prototype #225

Closed joaogui1 closed 2 years ago

joaogui1 commented 2 years ago

Description

Closes #218 Initiali implementation, needs testing

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 Jul 31, 2022 at 7:09PM (UTC)
vwxyzjn commented 2 years ago

@joaogui1 could you take a final look at https://cleanrl-git-fork-joaogui1-master-vwxyzjn.vercel.app/rl-algorithms/td3/#td3_continuous_action_jaxpy to see if there is anything missing?

joaogui1 commented 2 years ago

LGTM!