MTRL

Multi Task RL Algorithms

Introduction

MTRL is a library of multi-task reinforcement learning algorithms. It has two main components:

• Components and agents that implement the multi-task RL algorithms.

• Experiment setups that enable training/evaluation on different setups.

Together, these two components enable use of MTRL across different environments and setups.

List of publications & submissions using MTRL (please create a pull request to add the missing entries):

• Learning Robust State Abstractions for Hidden-Parameter Block MDPs

License

• MTRL uses MIT License.

• Terms of Use

• Privacy Policy

Citing MTRL

If you use MTRL in your research, please use the following BibTeX entry:

@Misc{Sodhani2021MTRL,
  author =       {Shagun Sodhani, Amy Zhang},
  title =        {MTRL - Multi Task RL Algorithms},
  howpublished = {Github},
  year =         {2021},
  url =          {https://github.com/facebookresearch/mtrl}
}

Setup

• Clone the repository: git clone git@github.com:facebookresearch/mtrl.git.

• Install dependencies: pip install -r requirements/dev.txt

Usage

• MTRL supports many different multi-task RL algorithms as described here.

• MTRL supports multi-task environments using MTEnv. These environments include MetaWorld and multi-task variants of DMControl Suite

• Refer the `tutorial]<https://mtrl.readthedocs.io/en/latest/pages/tutorials/overview.html>`_ to get started with MTRL.

Documentation

https://mtrl.readthedocs.io

Contributing to MTRL

There are several ways to contribute to MTRL.

1. Use MTRL in your research.

2. Contribute a new algorithm. The currently supported algorithms are listed here and are looking forward to adding more algorithms.

3. Check out the beginner-friendly issues on GitHub and contribute to fixing those issues.

4. Check out additional details here.

Community

Ask questions in the chat or github issues:

• Chat

• Issues