Shimmy

<p align="center"> <a href = "https://shimmy.farama.org/" target = "_blank"><img src="https://raw.githubusercontent.com/Farama-Foundation/Shimmy/main/shimmy-text.png" width="500px"/> </a> </p>

Shimmy is an API conversion tool providing Gymnasium and PettingZoo bindings for popular external reinforcement learning environments.

The documentation website is at shimmy.farama.org and we have a public discord server (which we also use to coordinate development work) that you can join here: https://discord.gg/nhvKkYa6qX

Supported APIs

OpenAI Gym

• Bindings to convert OpenAI Gym environments to Gymnasium.

DeepMind Control

• Bindings to convert DM Control environments to Gymnasium.

DeepMind Control: Multi-Agent

• Bindings to convert DM Control Soccer environments to PettingZoo.

OpenSpiel

• Bindings to convert OpenSpiel environments to PettingZoo.

Installation and Usage

To install Shimmy from PyPI:

pip install shimmy

To install required dependencies for environments, specify them as follows:

pip install shimmy[dm-control]

Choices: gym-v21, gym-v26, dm-control, dm-control-multi-agent, openspiel

Python version support

The underlying environment libraries impose ceilings that Shimmy itself cannot lift:

Extra	Highest supported Python	Why
gym-v21	3.10	gym 0.21.0 needs setuptools==65.5.0, which calls pkgutil.ImpImporter — removed in Python 3.12. Also needs pip<24.1 to accept its malformed metadata.
gym-v26	3.12	pins numpy<2.0; NumPy 1.26 ships wheels only through cp312. On newer Python pip falls back to building NumPy 1.x from source, which is slow and not guaranteed to work.
dm-control, dm-control-multi-agent	3.12	labmaze (transitive via dm_control) currently ships no wheels beyond cp312.
openspiel	3.14	open_spiel publishes wheels through cp314.

If you need a newer Python than an extra supports, use a separate virtual environment for that extra.

At a glance

This is an example of using Shimmy to convert DM Control environments into a Gymnasium compatible environment:

pythonCopy
import gymnasium as gym
from shimmy.registration import DM_CONTROL_SUITE_ENVS

env_ids = [f"dm_control/{'-'.join(item)}-v0" for item in DM_CONTROL_SUITE_ENVS]
print(env_ids)

env = gym.make(env_ids[0])
env_flatten = gym.wrappers.FlattenObservation(env)
print(env_ids[0])
print("===🌎", env.observation_space)
print("===🕹️", env.action_space)
print("---flattened 🌎", env_flatten.observation_space)
print("---flattened 🕹️", env_flatten.action_space)

bashCopy
['dm_control/acrobot-swingup-v0', 'dm_control/acrobot-swingup_sparse-v0', 'dm_control/ball_in_cup-catch-v0', 'dm_control/cartpole-balance-v0', 'dm_control/cartpole-balance_sparse-v0', 'dm_control/cartpole-swingup-v0', 'dm_control/cartpole-swingup_sparse-v0', 'dm_control/cartpole-two_poles-v0', 'dm_control/cartpole-three_poles-v0', 'dm_control/cheetah-run-v0', 'dm_control/dog-stand-v0', 'dm_control/dog-walk-v0', 'dm_control/dog-trot-v0', 'dm_control/dog-run-v0', 'dm_control/dog-fetch-v0', 'dm_control/finger-spin-v0', 'dm_control/finger-turn_easy-v0', 'dm_control/finger-turn_hard-v0', 'dm_control/fish-upright-v0', 'dm_control/fish-swim-v0', 'dm_control/hopper-stand-v0', 'dm_control/hopper-hop-v0', 'dm_control/humanoid-stand-v0', 'dm_control/humanoid-walk-v0', 'dm_control/humanoid-run-v0', 'dm_control/humanoid-run_pure_state-v0', 'dm_control/humanoid_CMU-stand-v0', 'dm_control/humanoid_CMU-run-v0', 'dm_control/lqr-lqr_2_1-v0', 'dm_control/lqr-lqr_6_2-v0', 'dm_control/manipulator-bring_ball-v0', 'dm_control/manipulator-bring_peg-v0', 'dm_control/manipulator-insert_ball-v0', 'dm_control/manipulator-insert_peg-v0', 'dm_control/pendulum-swingup-v0', 'dm_control/point_mass-easy-v0', 'dm_control/point_mass-hard-v0', 'dm_control/quadruped-walk-v0', 'dm_control/quadruped-run-v0', 'dm_control/quadruped-escape-v0', 'dm_control/quadruped-fetch-v0', 'dm_control/reacher-easy-v0', 'dm_control/reacher-hard-v0', 'dm_control/stacker-stack_2-v0', 'dm_control/stacker-stack_4-v0', 'dm_control/swimmer-swimmer6-v0', 'dm_control/swimmer-swimmer15-v0', 'dm_control/walker-stand-v0', 'dm_control/walker-walk-v0', 'dm_control/walker-run-v0']
dm_control/acrobot-swingup-v0
===🌎 Dict('orientations': Box(-inf, inf, (4,), float64), 'velocity': Box(-inf, inf, (2,), float64))
===🕹️ Box(-1.0, 1.0, (1,), float64)
---flattened 🌎 Box(-inf, inf, (6,), float64)
---flattened 🕹️ Box(-1.0, 1.0, (1,), float64)

See Basic Usage for more information.

Project Maintainers

Project Manager: Elliot Tower

Core Contributors: Jet Tai, Mark Towers

Maintenance for this project is also contributed by the broader Farama team: farama.org/team.

Citation

If you use Shimmy in your research, please cite:

@software{jun_jet_tai_2023_8140744,
  author       = {Jun Jet Tai and
                  Mark Towers and
                  Elliot Tower},
  title        = {{Shimmy: Gymnasium and PettingZoo Wrappers for
                   Commonly Used Environments}},
  month        = jun,
  year         = 2023,
  publisher    = {Zenodo},
  version      = {v1.1.0},
  doi          = {10.5281/zenodo.8140744},
  url          = {https://doi.org/10.5281/zenodo.8140744}
}