search

rail-berkeley / serl

SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
https://serl-robot.github.io/
MIT License
375 stars 42 forks source link

Support for Mujoco XLA #37

Closed shivanshpatel35 closed 6 months ago

shivanshpatel35 commented 7 months ago

Hi, Do you plan to support Mujoco XLA for simulation training in the near future?

jianlanluo commented 6 months ago

The simulator used in SERL is mainly for debugging purpose, we don't currently have a plan to further develop it. You are welcome to open a PR if you find adding Mujoco XLA is generically beneficial.