rsl-rl-lib

What it is and what it does

RSL-RL is a lightweight reinforcement learning library designed specifically for robotics research, built on PyTorch with native GPU acceleration and multi-GPU training support. It provides implementations of common RL algorithms—notably PPO and Student-Teacher Distillation—in a minimal, readable codebase that prioritizes rapid prototyping over the complexity of larger frameworks. The library is used as the training backend for Isaac Lab, Legged Gym, mjlab, and MuJoCo Playground.

The package depends on torch, torchvision, tensordict, numpy, tensorboard, GitPython, onnx, and onnxscript. It requires Python 3.9 or later and is distributed as a pure Python wheel, making installation straightforward. The library is actively maintained (latest release 30 days old, 2885 GitHub stars) and has no known security vulnerabilities.

Use it for:

• Training locomotion policies for legged robots using PPO in Isaac Sim or Isaac Gym environments
• Prototyping new RL algorithms without modifying a large framework codebase
• Scaling training across multiple GPUs for faster policy convergence in robotics tasks
• Integrating RL training into existing robot learning pipelines via Isaac Lab or Legged Gym
• Exporting trained policies to ONNX format for deployment on robot hardware

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

RSL-RL is a GPU-accelerated reinforcement learning library for robotics research, providing implementations of algorithms like PPO with multi-GPU training support and a minimal, extensible codebase.

Yes, if you are doing robotics research with PyTorch and need a lightweight, actively maintained RL training library. The low install friction, permissive license, active maintenance, and zero known vulnerabilities make it a solid choice. Install it if you are working with Isaac Lab, Legged Gym, or similar robot learning environments; otherwise, verify that its algorithm implementations and API match your specific needs.

Install

rsl-rl-lib on PyPI

pip install rsl-rl-lib

uv add rsl-rl-lib

poetry add rsl-rl-lib

Installing rsl-rl-lib

Before you install

Low install friction with a pure Python wheel distribution. Active maintenance with a recent release (30 days ago) and steady repository activity. Eight runtime dependencies, primarily PyTorch ecosystem packages, are standard for GPU-accelerated ML work.

License in practice

BSD-3-Clause is a permissive license allowing commercial and private use with minimal restrictions, making the package suitable for both research and production robotics projects.

Quickstart

pip install rsl-rl-lib

from rsl_rl import ... # import desired algorithm or environment interface
# Usage depends on integration with Isaac Lab, Legged Gym, or similar robot learning environment

Requires Python 3.9 or later; GPU drivers and CUDA toolkit recommended for GPU acceleration, though specific requirements depend on torch installation.

Verify before relying

• Whether CPU-only PyTorch is supported or if GPU/CUDA is mandatory
• Specific algorithm implementations available beyond PPO and Student-Teacher Distillation
• API stability and backward compatibility guarantees across releases

Package facts

Evidence: rsl_rl_lib-5.4.2-py3-none-any.whl

Keywords: reinforcement-learning, robotics

Tags

More Artificial Intelligence packages

Further reading