Note

From Ray 2.6.0 onwards, RLlib is adopting a new stack for training and model customization, gradually replacing the ModelV2 API and some convoluted parts of Policy API with the RLModule API. Click here for details.

用户指南

RLlib Feature Guides

Advanced Features of the RLlib Python API

Working With Models, Preprocessors and Action Distributions

Checkpointing your Algorithms and Policies, and Exporting your Models

How To Customize Your Policies?

How To Use Sample Collections and Trajectory Views?

Working With Offline Data

Working with ReplayBuffers

How To Contribute To RLlib?

How To Work With the RLlib CLI?

How To Use the RLlib Catalogs