Welcome to OpenRL’s documentation!

中文文档 | GitHub

User Guide

• OpenRL Introduction
  • OpenRL Reinforcement Learning Framework
  • Citing OpenRL
• Quick Start Guide
  • Installation Instructions
  • Train Your First Agent
  • Multi-Agent Training
  • Train Natural Language Dialogue Task
• Integrate User-defined Environments
  • Integrate an Environment Compliant with the Gymnasium Interface
  • Integrate Environments Compliant with OpenAI Gym Interface
  • Integrate Environments Compliant with PettingZoo Interface
  • Customize Environment Creation through make_custom_envs
  • Customize Environment Creation with make
  • Integrate Existing Environments through Custom Wrappers
• Callbacks
  • Built-in Callbacks
  • Customize and Register Callback
• Self-Play Training
  • Performing Self-Play Training with OpenRL
• Arena
  • Evaluating Agents Through the Arena
  • Performing Local Evaluation of Agents Submitted to the JiDi Platform Using OpenRL
• Loading Stable-baselines3 Models from Hugging Face
  • Environment Setup
  • Downloading the Model
  • Load Stable-baselines3 Model and Test
  • Load Stable-baselines3 Model and Train
• API Doc
  • Subpackages