Home

Awesome

CircleCI PyPI - License PyPI - Python Version Code style: black Zulip Chat

MTEnv

MultiTask Environments for Reinforcement Learning.

Contents

  1. Introduction

  2. Installation

  3. Usage

  4. Documentation

  5. Contributing to MTEnv

  6. Community

  7. Acknowledgements

Introduction

MTEnv is a library to interface with environments for multi-task reinforcement learning. It has two main components:

Together, these two components should provide a standard interface for multi-task RL environments and make it easier to reuse components and tools across environments.

You can read more about the difference between MTEnv and single-task environments here.

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

License

Citing MTEnv

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

@Misc{Sodhani2021MTEnv,
  author =       {Shagun Sodhani and Ludovic Denoyer and Pierre-Alexandre Kamienny and Olivier Delalleau},
  title =        {MTEnv - Environment interface for mulit-task reinforcement learning},
  howpublished = {Github},
  year =         {2021},
  url =          {https://github.com/facebookresearch/mtenv}
}

Installation

MTEnv has two components - a core API and environments that implement the API.

The Core API can be installed via pip install mtenv or pip install git+https://github.com/facebookresearch/mtenv.git@main#egg=mtenv

The list of environments, that implement the API, is available here. Any of these environments can be installed via pip install git+https://github.com/facebookresearch/mtenv.git@main#egg="mtenv[env_name]". For example, the MetaWorld environment can be installed via pip install git+https://github.com/facebookresearch/mtenv.git@main#egg="mtenv[metaworld]".

All the environments can be installed at once using pip install git+https://github.com/facebookresearch/mtenv.git@main#egg="mtenv[all]". However, note that some environments may have incompatible dependencies.

MTEnv can also be installed from the source by first cloning the repo (git clone git@github.com:facebookresearch/mtenv.git), cding into the directory cd mtenv, and then using the pip commands as described above. For example, pip install mtenv to install the core API, and pip install "mtenv[env_name]" to install a particular environment.

Usage

MTEnv provides an interface very similar to the standard gym environments. One key difference between multi-task environments (that implement the MTEnv interface) and single-task environments is in terms of observation that they return.

MultiTask Observation

The multi-task environments return a dictionary as the observation. This dictionary has two keys: (i) env_obs, which maps to the observation from the environment (i.e., the observation that a single task environments return), and (ii) task_obs, which maps to the task-specific information from the environment. In the simplest case, task_obs can be an integer denoting the task index. In other cases, task_obs can provide richer information.

from mtenv import make
env = make("MT-MetaWorld-MT10-v0")
obs = env.reset()
print(obs)
# {'env_obs': array([-0.03265039,  0.51487777,  0.2368754 , -0.06968209,  0.6235982 ,
#    0.01492813,  0.        ,  0.        ,  0.        ,  0.03933976,
#    0.89743189,  0.01492813]), 'task_obs': 1}
action = env.action_space.sample()
print(action)
# array([-0.76422   , -0.15384133,  0.74575615, -0.11724994], dtype=float32)
obs, reward, done, info = env.step(action)
print(obs)
# {'env_obs': array([-0.02583682,  0.54065546,  0.22773503, -0.06968209,  0.6235982 ,
#    0.01494118,  0.        ,  0.        ,  0.        ,  0.03933976,
#    0.89743189,  0.01492813]), 'task_obs': 1}

Documentation

https://mtenv.readthedocs.io

Contributing to MTEnv

There are several ways to contribute to MTEnv.

  1. Use MTEnv in your research.

  2. Contribute a new environment. We support many environments via MTEnv and are looking forward to adding more environments. Contributors will be added as authors of the library. You can learn more about the workflow of adding an environment here.

  3. Check out the good-first-issues on GitHub and contribute to fixing those issues.

  4. Check out additional details here.

Community

Ask questions in the chat or github issues:

Acknowledgements