Metadata-Version: 2.4
Name: skrl
Version: 2.1.0
Summary: Modular and flexible library for reinforcement learning on PyTorch and JAX
Author: Toni-SM
Maintainer: Toni-SM
License: MIT License
Project-URL: Homepage, https://github.com/Toni-SM/skrl
Project-URL: Documentation, https://skrl.readthedocs.io
Project-URL: Discussions, https://github.com/Toni-SM/skrl/discussions
Project-URL: Bug Reports, https://github.com/Toni-SM/skrl/issues
Project-URL: Say Thanks!, https://github.com/Toni-SM
Project-URL: Source, https://github.com/Toni-SM/skrl
Keywords: reinforcement-learning,machine-learning,reinforcement,machine,learning,rl
Classifier: License :: OSI Approved :: MIT License
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Programming Language :: Python :: 3
Classifier: Operating System :: OS Independent
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: gymnasium
Requires-Dist: packaging
Requires-Dist: tensorboard
Requires-Dist: tqdm
Provides-Extra: torch
Requires-Dist: torch>=1.11; extra == "torch"
Provides-Extra: jax
Requires-Dist: jax>=0.4.31; extra == "jax"
Requires-Dist: jaxlib>=0.4.31; extra == "jax"
Requires-Dist: flax>=0.9.0; extra == "jax"
Requires-Dist: optax; extra == "jax"
Provides-Extra: warp
Requires-Dist: warp-lang>=1.12; extra == "warp"
Requires-Dist: warp-nn>=0.1; extra == "warp"
Provides-Extra: all
Requires-Dist: torch>=1.11; extra == "all"
Requires-Dist: jax>=0.4.31; extra == "all"
Requires-Dist: jaxlib>=0.4.31; extra == "all"
Requires-Dist: flax>=0.9.0; extra == "all"
Requires-Dist: optax; extra == "all"
Requires-Dist: warp-lang>=1.12; extra == "all"
Requires-Dist: warp-nn>=0.1; extra == "all"
Provides-Extra: tests
Requires-Dist: pytest; extra == "tests"
Requires-Dist: pytest-html; extra == "tests"
Requires-Dist: pytest-cov; extra == "tests"
Requires-Dist: hypothesis; extra == "tests"
Requires-Dist: pyyaml; extra == "tests"
Dynamic: license-file

[![pypi](https://img.shields.io/pypi/v/skrl)](https://pypi.org/project/skrl)
[<img src="https://img.shields.io/badge/%F0%9F%A4%97%20models-hugging%20face-F8D521">](https://huggingface.co/skrl)
![discussions](https://img.shields.io/github/discussions/Toni-SM/skrl)
<br>
[![license](https://img.shields.io/github/license/Toni-SM/skrl)](https://github.com/Toni-SM/skrl)
<span>&nbsp;&nbsp;&nbsp;&nbsp;</span>
[![docs](https://readthedocs.org/projects/skrl/badge/?version=latest)](https://skrl.readthedocs.io/en/latest/?badge=latest)
[![pre-commit](https://github.com/Toni-SM/skrl/actions/workflows/pre-commit.yml/badge.svg)](https://github.com/Toni-SM/skrl/actions/workflows/pre-commit.yml)
[![pytest-torch](https://github.com/Toni-SM/skrl/actions/workflows/tests-torch.yml/badge.svg)](https://github.com/Toni-SM/skrl/actions/workflows/tests-torch.yml)
[![pytest-jax](https://github.com/Toni-SM/skrl/actions/workflows/tests-jax.yml/badge.svg)](https://github.com/Toni-SM/skrl/actions/workflows/tests-jax.yml)
[![pytest-warp](https://github.com/Toni-SM/skrl/actions/workflows/tests-warp.yml/badge.svg)](https://github.com/Toni-SM/skrl/actions/workflows/tests-warp.yml)

<br>
<p align="center">
  <a href="https://skrl.readthedocs.io">
  <img width="300rem" src="https://raw.githubusercontent.com/Toni-SM/skrl/main/docs/source/_static/data/logo-light-mode.png">
  </a>
</p>
<h2 align="center" style="border-bottom: 0 !important;">SKRL - Reinforcement Learning library</h2>
<br>

**Documentation:** <strong>https://skrl.readthedocs.io</strong>

**Description**: ``skrl`` is an open-source modular library for Reinforcement Learning written in Python
(implemented in [PyTorch](https://pytorch.org/), [JAX](https://jax.readthedocs.io) and [NVIDIA Warp](https://nvidia.github.io/warp/))
and designed with a focus on modularity, readability, simplicity, and transparency of algorithm implementation.
In addition to supporting
OpenAI [Gym](https://www.gymlibrary.dev),
Farama [Gymnasium](https://gymnasium.farama.org) and [PettingZoo](https://pettingzoo.farama.org),
[ManiSkill](https://maniskill.readthedocs.io/en/latest/index.html),
among other environment interfaces, it allows loading and configuring
NVIDIA [Isaac Lab](https://isaac-sim.github.io/IsaacLab/index.html) and
[MuJoCo Playground](https://playground.mujoco.org/)
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.

<br>

### Refer to the documentation for details and examples: https://skrl.readthedocs.io

<br>

> **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.

<br>

### 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}
}
```
