rsl_rl
- Software
- Humanoids and robot learning
- Library
A lightweight, GPU-accelerated Python library for robot learning research, offering PPO and student-teacher distillation with minimal, easy-to-extend code.
Source on GitHub: github.com/leggedrobotics/rsl_rl (opens in a new tab). Facts read at commit a87ef38 (opens in a new tab).
Licenses
- Code
- BSD-3-Clause (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (BSD-3-Clause) at commit a87ef38 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Designed as a compact codebase so researchers can prototype new ideas without modifying large libraries.
- Provides common robot-learning algorithms, including PPO and Student-Teacher Distillation.
- Supports native multi-GPU training for high-throughput runs.
- Installable from PyPI as a dependency, or cloned and installed in editable mode for development.
- Additional community-contributed algorithms and models are kept on a separate extras branch.
- Used as the learning backend by Isaac Lab, Legged Gym, mjlab, and MuJoCo Playground.
Written by Robotheca from the project's README (opens in a new tab) at commit a87ef38.
Getting started
- Difficulty
- Advanced
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 12 Oct 2026 on main
- Latest release
- v5.5.1 (9 Sept 2026)
Checked on GitHub on 16 Oct 2026.
Links
Robots on Robotheca that use it
No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.
Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.