[](https://github.com/catalyst-team/catalyst)
**Accelerated RL**
[](http://66.248.205.49:8111/project.html?projectId=Catalyst&tab=projectOverview&guest=1)
[](https://www.codefactor.io/repository/github/catalyst-team/catalyst)
[](https://pypi.org/project/catalyst/)
[](https://catalyst-team.github.io/catalyst/index.html)
[](https://pepy.tech/project/catalyst)
[](https://twitter.com/CatalystTeam)
[](https://t.me/catalyst_team)
[](https://join.slack.com/t/catalyst-team-devs/shared_invite/zt-d9miirnn-z86oKDzFMKlMG4fgFdZafw)
[](https://github.com/catalyst-team/catalyst/graphs/contributors)
PyTorch framework for RL research.
It was developed with a focus on reproducibility,
fast experimentation and code/ideas reusing.
Being able to research/develop something new,
rather than write another regular train loop.
Break the cycle - use the Catalyst!
Project [manifest](https://github.com/catalyst-team/catalyst/blob/master/MANIFEST.md). Part of [PyTorch Ecosystem](https://pytorch.org/ecosystem/). Part of [Catalyst Ecosystem](https://docs.google.com/presentation/d/1D-yhVOg6OXzjo9K_-IS5vSHLPIUxp1PEkFGnpRcNCNU/edit?usp=sharing):
- [Alchemy](https://github.com/catalyst-team/alchemy) - Experiments logging & visualization
- [Catalyst](https://github.com/catalyst-team/catalyst) - Accelerated Deep Learning Research and Development
- [Reaction](https://github.com/catalyst-team/reaction) - Convenient Deep Learning models serving
[Catalyst at AI Landscape](https://landscape.lfai.foundation/selected=catalyst).
---
## Installation
Common installation:
```bash
pip install -U catalyst-rl
```
Catalyst.RL is compatible with: Python 3.6+. PyTorch 1.0.0+.
## Getting started
For Catalyst.RL introduction, please follow [OpenAI Gym example](https://github.com/catalyst-team/catalyst-rl/tree/master/examples/rl_gym).
#### Docs and examples
- [Demo with minimal examples](https://github.com/catalyst-team/catalyst/tree/master/examples/notebooks/demo.ipynb) for CV, NLP, RecSys and GANs [](https://colab.research.google.com/github/catalyst-team/catalyst/blob/master/examples/notebooks/demo.ipynb)
- Detailed [classification tutorial](https://github.com/catalyst-team/catalyst/tree/master/examples/notebooks/classification-tutorial.ipynb) [](https://colab.research.google.com/github/catalyst-team/catalyst/blob/master/examples/notebooks/classification-tutorial.ipynb)
- Advanced [segmentation tutorial](https://github.com/catalyst-team/catalyst/tree/master/examples/notebooks/segmentation-tutorial.ipynb) [](https://colab.research.google.com/github/catalyst-team/catalyst/blob/master/examples/notebooks/segmentation-tutorial.ipynb)
- Comprehensive [classification pipeline](https://github.com/catalyst-team/classification)
- Binary and semantic [segmentation pipeline](https://github.com/catalyst-team/segmentation)
API documentation and an overview of the library can be found here
[](https://catalyst-team.github.io/catalyst/index.html).
In the **[examples folder](examples)**
of the repository, you can find advanced tutorials and Catalyst best practices.
##### Infos
To learn more about Catalyst internals and to be aware of the most important features, you can read **[Catalyst-info](https://github.com/catalyst-team/catalyst-info)** – our blog where we regularly write facts about the framework.
We also supervise **[Awesome Catalyst list](https://github.com/catalyst-team/awesome-catalyst-list)** – Catalyst-powered projects, tutorials and talks.
Feel free to make a PR with your project to the list. And don't forget to check out current list, there are many interesting projects.
##### Releases
We deploy a major release once a month with a name like `YY.MM`.
And micro-releases with framework improvements during a month in the format `YY.MM.#`.
You can view the changelog on the **[GitHub Releases](https://github.com/catalyst-team/catalyst/releases)** page.
Current version: [](https://pypi.org/project/catalyst/)
## Overview
Catalyst.RL helps you write compact
but full-featured RL pipelines in a few lines of code.
You get a training loop with metrics, early-stopping, model checkpointing
and other features without the boilerplate.
#### Features
- Universal train/inference loop.
- Configuration files for model/data hyperparameters.
- Reproducibility – all source code and environment variables will be saved.
- Callbacks – reusable train/inference pipeline parts.
- Training stages support.
- Easy customization.
- PyTorch best practices (SWA, AdamW, Ranger optimizer, OneCycle, FP16 and more).
#### Structure
- **RL** – scalable Reinforcement Learning,
all popular model-free algorithms implementations and their improvements
with distributed training support.
- **contrib** - additional modules contributed by Catalyst users.
- **utils** - different useful utils for Deep Learning research.
## Contribution guide
We appreciate all contributions.
If you are planning to contribute back bug-fixes,
please do so without any further discussion.
If you plan to contribute new features, utility functions or extensions,
please first open an issue and discuss the feature with us.
- Please see the [contribution guide](CONTRIBUTING.md) for more information.
- By participating in this project, you agree to abide by its [Code of Conduct](CODE_OF_CONDUCT.md).
## License
This project is licensed under the Apache License, Version 2.0 see the [LICENSE](LICENSE) file for details
[](LICENSE)
## Citation
Please use this bibtex if you want to cite this repository in your publications:
@misc{catalyst,
author = {Kolesnikov, Sergey},
title = {Accelerated RL.},
year = {2018},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/catalyst-team/catalyst-rl}},
}