Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/Toni-SM/skrl
Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab
https://github.com/Toni-SM/skrl
deep-learning deepmind gym gymnasium isaac-gym isaac-lab isaac-orbit isaac-sim isaaclab jax machine-learning nvidia-omniverse openai-gym python pytorch reinforcement-learning rl robosuite robotics skrl
Last synced: 2 months ago
JSON representation
Modular reinforcement learning library (on PyTorch and JAX) with support for NVIDIA Isaac Gym, Omniverse Isaac Gym and Isaac Lab
- Host: GitHub
- URL: https://github.com/Toni-SM/skrl
- Owner: Toni-SM
- License: mit
- Created: 2021-10-18T07:53:11.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2024-10-16T20:43:45.000Z (3 months ago)
- Last Synced: 2024-10-18T18:08:11.959Z (3 months ago)
- Topics: deep-learning, deepmind, gym, gymnasium, isaac-gym, isaac-lab, isaac-orbit, isaac-sim, isaaclab, jax, machine-learning, nvidia-omniverse, openai-gym, python, pytorch, reinforcement-learning, rl, robosuite, robotics, skrl
- Language: Python
- Homepage: https://skrl.readthedocs.io/
- Size: 7.13 MB
- Stars: 533
- Watchers: 9
- Forks: 51
- Open Issues: 11
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.md
- License: LICENSE
Awesome Lists containing this project
- awesome-isaac-gym - skrl - Modular RL library (🛠Tools & Libraries / RL Frameworks)
- awesome-production-machine-learning - skrl - SM/skrl.svg?style=social) - skrl is an open-source modular library for Reinforcement Learning written in Python (using PyTorch) and designed with a focus on readability, simplicity, and transparency of algorithm implementation. (Industry Strength RL)
README
[](https://pypi.org/project/skrl)
[
](https://huggingface.co/skrl)
[](https://github.com/Toni-SM/skrl)
   Â
[](https://skrl.readthedocs.io/en/latest/?badge=latest)
[](https://github.com/Toni-SM/skrl/actions/workflows/python-test.yml)
[](https://github.com/Toni-SM/skrl/actions/workflows/pre-commit.yml)
SKRL - Reinforcement Learning library
**skrl** is an open-source modular library for Reinforcement Learning written in Python (on top of [PyTorch](https://pytorch.org/) and [JAX](https://jax.readthedocs.io)) and designed with a focus on modularity, readability, simplicity, and transparency of algorithm implementation. In addition to supporting the OpenAI [Gym](https://www.gymlibrary.dev), Farama [Gymnasium](https://gymnasium.farama.org) and [PettingZoo](https://pettingzoo.farama.org), Google [DeepMind](https://github.com/deepmind/dm_env) and [Brax](https://github.com/google/brax), among other environment interfaces, it allows loading and configuring NVIDIA [Isaac Lab](https://isaac-sim.github.io/IsaacLab/index.html) (as well as [Isaac Gym](https://developer.nvidia.com/isaac-gym/) and [Omniverse Isaac Gym](https://github.com/isaac-sim/OmniIsaacGymEnvs)) environments, enabling agents' simultaneous training by scopes (subsets of environments among all available environments), which may or may not share resources, in the same run.
### Please, visit the documentation for usage details and examples
https://skrl.readthedocs.io
> **Note:** This project is under **active continuous development**. Please make sure you always have the latest version. Visit the [develop](https://github.com/Toni-SM/skrl/tree/develop) branch or its [documentation](https://skrl.readthedocs.io/en/develop) to access the latest updates to be released.
### Citing this library
To cite this library in publications, please use the following reference:
```bibtex
@article{serrano2023skrl,
author = {Antonio Serrano-Muñoz and Dimitrios Chrysostomou and Simon Bøgh and Nestor Arana-Arexolaleiba},
title = {skrl: Modular and Flexible Library for Reinforcement Learning},
journal = {Journal of Machine Learning Research},
year = {2023},
volume = {24},
number = {254},
pages = {1--9},
url = {http://jmlr.org/papers/v24/23-0112.html}
}
```