{"id":13771446,"url":"https://github.com/facebookresearch/mtrl","last_synced_at":"2025-05-11T04:30:43.219Z","repository":{"id":41079727,"uuid":"334282351","full_name":"facebookresearch/mtrl","owner":"facebookresearch","description":"Multi Task RL Baselines","archived":true,"fork":false,"pushed_at":"2021-12-31T03:40:39.000Z","size":537,"stargazers_count":226,"open_issues_count":13,"forks_count":27,"subscribers_count":9,"default_branch":"main","last_synced_at":"2024-12-17T01:37:45.096Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/facebookresearch.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":".github/CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":".github/CODE_OF_CONDUCT.md","threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2021-01-29T22:59:54.000Z","updated_at":"2024-11-14T07:36:58.000Z","dependencies_parsed_at":"2022-07-14T08:09:00.848Z","dependency_job_id":null,"html_url":"https://github.com/facebookresearch/mtrl","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2Fmtrl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2Fmtrl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2Fmtrl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/facebookresearch%2Fmtrl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/facebookresearch","download_url":"https://codeload.github.com/facebookresearch/mtrl/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253518941,"owners_count":21921074,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-03T17:00:51.569Z","updated_at":"2025-05-11T04:30:42.015Z","avatar_url":"https://github.com/facebookresearch.png","language":"Python","funding_links":[],"categories":["Codebase"],"sub_categories":["Recommendation"],"readme":"[![CircleCI](https://circleci.com/gh/facebookresearch/mtrl.svg?style=svg\u0026circle-token=8cc8eb1b9666a65e27a21c39b5d5398744365894)](https://circleci.com/gh/facebookresearch/mtrl)\n[![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](https://github.com/facebookresearch/mtrl/blob/main/LICENSE)\n[![Python 3.6+](https://img.shields.io/badge/python-3.6+-blue.svg)](https://www.python.org/downloads/release/python-360/)\n[![Code style: black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black)\n[![Zulip Chat](https://img.shields.io/badge/zulip-join_chat-brightgreen.svg)](https://mtenv.zulipchat.com)\n\n# MTRL\nMulti Task RL Algorithms\n\n## Contents\n\n1. [Introduction](#Introduction)\n\n2. [Setup](#Setup)\n\n3. [Usage](#Usage)\n\n4. [Documentation](#Documentation)\n\n5. [Contributing to MTRL](#Contributing-to-MTRL)\n\n6. [Community](#Community)\n\n7. [Acknowledgements](#Acknowledgements)\n\n## Introduction\n\nMTRL is a library of multi-task reinforcement learning algorithms. It has two main components:\n\n* [Building blocks](https://github.com/facebookresearch/mtrl/tree/main/mtrl/agent/components) and [agents](https://github.com/facebookresearch/mtrl/tree/main/mtrl/agent) that implement the multi-task RL algorithms.\n\n* [Experiment setups](https://github.com/facebookresearch/mtrl/tree/main/mtrl/experiment) that enable training/evaluation on different setups. \n\nTogether, these two components enable use of MTRL across different environments and setups.\n\n### List of publications \u0026 submissions using MTRL (please create a pull request to add the missing entries):\n\n* [Learning Robust State Abstractions for Hidden-Parameter Block MDPs](https://arxiv.org/abs/2007.07206)\n* [Multi-Task Reinforcement Learning with Context-based Representations](https://arxiv.org/abs/2102.06177)\n    *  We use the `af8417bfc82a3e249b4b02156518d775f29eb289` commit for the MetaWorld environments for our experiments.\n\n### License\n\n* MTRL uses [MIT License](https://github.com/facebookresearch/mtrl/blob/main/LICENSE).\n\n* [Terms of Use](https://opensource.facebook.com/legal/terms)\n\n* [Privacy Policy](https://opensource.facebook.com/legal/privacy)\n\n### Citing MTRL\n\nIf you use MTRL in your research, please use the following BibTeX entry:\n```\n@Misc{Sodhani2021MTRL,\n  author =       {Shagun Sodhani and Amy Zhang},\n  title =        {MTRL - Multi Task RL Algorithms},\n  howpublished = {Github},\n  year =         {2021},\n  url =          {https://github.com/facebookresearch/mtrl}\n}\n```\n\n## Setup\n\n* Clone the repository: `git clone git@github.com:facebookresearch/mtrl.git`.\n\n* Install dependencies: `pip install -r requirements/dev.txt`\n\n## Usage\n\n* MTRL supports 8 different multi-task RL algorithms as described [here](https://mtrl.readthedocs.io/en/latest/pages/tutorials/overview.html).\n\n* MTRL supports multi-task environments using [MTEnv](https://github.com/facebookresearch/mtenv). These environments include [MetaWorld](https://meta-world.github.io/) and multi-task variants of [DMControl Suite](https://github.com/deepmind/dm_control)\n\n* Refer the [tutorial](https://mtrl.readthedocs.io/en/latest/pages/tutorials/overview.html) to get started with MTRL.\n\n## Documentation\n\n[https://mtrl.readthedocs.io](https://mtrl.readthedocs.io)\n\n## Contributing to MTRL\n\nThere are several ways to contribute to MTRL.\n\n1. Use MTRL in your research.\n\n2. Contribute a new algorithm. We currently support [8 multi-task RL algorithms](https://mtrl.readthedocs.io/en/latest/pages/algorithms/supported.html) and are looking forward to adding more environments.\n\n3. Check out the [good-first-issues](https://github.com/facebookresearch/mtrl/pulls?q=is%3Apr+is%3Aopen+label%3A%22good+first+issue%22) on GitHub and contribute to fixing those issues.\n\n4. Check out additional details [here](https://github.com/facebookresearch/mtrl/blob/main/.github/CONTRIBUTING.md).\n\n## Community\n\nAsk questions in the chat or github issues:\n* [Chat](https://mtenv.zulipchat.com)\n* [Issues](https://github.com/facebookresearch/mtrl/issues)\n\n## Acknowledgements\n\n* Our implementation of SAC is inspired by Denis Yarats' implementation of [SAC](https://github.com/denisyarats/pytorch_sac).\n* Project file pre-commit, mypy config, towncrier config, circleci etc are based on same files from [Hydra](https://github.com/facebookresearch/hydra).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2Fmtrl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffacebookresearch%2Fmtrl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffacebookresearch%2Fmtrl/lists"}