SKRL
A modular Python library for Reinforcement Learning with support for PyTorch, JAX, NVIDIA Warp, and multiple environment interfaces.
What is SKRL?
skrl is an open-source modular library for Reinforcement Learning (RL) written in Python. It provides implementations in PyTorch, JAX, and NVIDIA Warp, supporting various environment interfaces like Gymnasium, NVIDIA Isaac Lab, and MuJoCo Playground. The library focuses on enabling flexible agent training, including simultaneous training across environment subsets.
Researchers, developers, and students working on Reinforcement Learning projects who need a modular, transparent, and multi-backend library for experimenting with RL algorithms across diverse environments.
Developers choose skrl for its modular design, support for multiple computation backends (PyTorch, JAX, NVIDIA Warp), and compatibility with a wide range of RL environments, which simplifies experimentation and deployment in complex RL scenarios.
Overview
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
Use Cases
Best For
- Training RL agents with PyTorch, JAX, or NVIDIA Warp backends
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
