User Guides

Note

Ray 2.40 uses RLlib’s new API stack by default. The Ray team has mostly completed transitioning algorithms, example scripts, and documentation to the new code base.

If you’re still using the old API stack, see New API stack migration guide for details on how to migrate.

RLlib Feature Guides

Advanced features of the RLlib python API

Injecting custom code into RLlib through callbacks

Logging metrics and statistics from custom code

Checkpointing your experiments and models

How to process trajectories through episodes

Offline RL with offline datasets

Working with replay buffers

Contribute to RLlib

How to run RLlib experiments at scale