> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/isaaclab/2.2/overview/reinforcement-learning/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/isaaclab/_mcp/server.

# Reinforcement Learning

Isaac Lab supports multiple reinforcement learning frameworks.
In this section, we show existing scripts for running reinforcement learning
with supported RL libraries and provide a comparison of the supported
learning frameworks.

## Docs

- [Reinforcement Learning Scripts](https://docs.nvidia.com/isaaclab/2.2/overview/reinforcement-learning/reinforcement-learning-scripts.md): 
- [Reinforcement Learning Library Comparison](https://docs.nvidia.com/isaaclab/2.2/overview/reinforcement-learning/reinforcement-learning-library-comparison.md): 
- [Performance Benchmarks](https://docs.nvidia.com/isaaclab/2.2/overview/reinforcement-learning/performance-benchmarks.md): 
- [Debugging and Training Guide](https://docs.nvidia.com/isaaclab/2.2/overview/reinforcement-learning/debugging-and-training-guide.md):