skrl
- Software
- Humanoids and robot learning
- Library
An open-source modular Python library for reinforcement learning, implemented in PyTorch, JAX and NVIDIA Warp, focused on modularity, readability and transparency.
Source on GitHub: github.com/Toni-SM/skrl (opens in a new tab). Facts read at commit c2995b3 (opens in a new tab).
Licenses
- Code
- MIT (opens in a new tab)
Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit c2995b3 (opens in a new tab), on 16 Oct 2026.
- Commercial use
- Yes
What it does
- Supports environment interfaces such as Gym, Gymnasium, PettingZoo and ManiSkill.
- Loads and configures NVIDIA Isaac Lab and MuJoCo Playground environments.
- Enables simultaneous training of agents by scopes, which may or may not share resources, in the same run.
- Documentation with details and examples is hosted on the project's documentation site.
- Under active continuous development; the develop branch holds the latest updates.
Written by Robotheca from the project's README (opens in a new tab) at commit c2995b3.
Getting started
- Difficulty
- Intermediate
- How to start
- The project's website (opens in a new tab)
Maintenance
- Status
- Active: a commit in the last 90 days
- Newest commit
- 16 Oct 2026 on develop
- Latest release
- skrl-v2.1.0 (11 May 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.