Farama FoundationApr 25, 2023
We are excited to announce the mature release of Shimmy, an API compatibility tool for converting popular external RL environments to the Gymnasium and PettingZoo APIs. This allows environments such as DM Control to be used with standard training libraries like stable-baselines3 馃殌
Show threadFarama FoundationApr 25, 2023

Shimmy鈥檚 documentation can be found at https://shimmy.farama.org, containing an overview of each environment with screenshots, installation instructions, full usage scripts, and API information.

For more information, see our blog post:
https://farama.org/Announcing-Shimmy

Shimmy Documentation

Shimmy
Show threadFarama FoundationApr 25, 2023

DM Control: DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
https://github.com/deepmind/dm_control

Shimmy documentation: https://shimmy.farama.org/environments/dm_control/

GitHub - deepmind/dm_control: DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo. - GitHub - deepmind/dm_control: DeepMind's software stack for physics-based sim...

GitHub
Show threadFarama FoundationApr 25, 2023

DM Lab: A customisable 3D platform for agent-based AI research.
https://github.com/deepmind/lab

Shimmy documentation: https://shimmy.farama.org/environments/dm_lab/

GitHub - deepmind/lab: A customisable 3D platform for agent-based AI research

A customisable 3D platform for agent-based AI research - GitHub - deepmind/lab: A customisable 3D platform for agent-based AI research

GitHub
Show threadFarama FoundationApr 25, 2023

Behavior Suite: a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent.
https://github.com/deepmind/bsuite

Shimmy documentation: https://shimmy.farama.org/environments/bsuite/

GitHub - deepmind/bsuite: bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent - GitHub - deepmind/bsuite: bsuite is a collection of carefully-de...

GitHub
Show threadFarama FoundationApr 25, 2023

OpenAI Gym: A toolkit for developing and comparing reinforcement learning algorithms.
https://github.com/openai/gym

Shimmy documentation: https://shimmy.farama.org/environments/gym/

GitHub - openai/gym: A toolkit for developing and comparing reinforcement learning algorithms.

A toolkit for developing and comparing reinforcement learning algorithms. - GitHub - openai/gym: A toolkit for developing and comparing reinforcement learning algorithms.

GitHub
Show threadFarama Foundation

Arcade Learning Environment (ALE): a simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games.
https://github.com/mgbellemare/Arcade-Learning-Environment

Shimmy documentation: https://shimmy.farama.org/environments/atari/

GitHub - mgbellemare/Arcade-Learning-Environment: The Arcade Learning Environment (ALE) -- a platform for AI research.

The Arcade Learning Environment (ALE) -- a platform for AI research. - GitHub - mgbellemare/Arcade-Learning-Environment: The Arcade Learning Environment (ALE) -- a platform for AI research.

GitHub
Apr 25, 2023 at 8:23pmWeb
Show threadFarama FoundationApr 25, 2023

DM Control Soccer: DeepMind MuJoCo Multi-Agent Soccer Environment.
https://github.com/deepmind/dm_control/blob/main/dm_control/locomotion/soccer/README.md

Shimmy documentation: https://shimmy.farama.org/environments/dm_multi/

dm_control/README.md at main 路 deepmind/dm_control

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo. - dm_control/README.md at main 路 deepmind/dm_control

GitHub
Show threadFarama FoundationApr 25, 2023

OpenSpiel: a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
https://github.com/deepmind/open_spiel

Shimmy documentation: https://shimmy.farama.org/environments/open_spiel/

GitHub - deepmind/open_spiel: OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games. - GitHub - deepmind/open_spiel: OpenSpiel is a collection of en...

GitHub
Show threadFarama FoundationApr 25, 2023

Melting Pot: a suite of test scenarios for multi-agent reinforcement learning, assessing generalization to novel social situations.
https://github.com/deepmind/meltingpot

Shimmy documentation: https://shimmy.farama.org/environments/meltingpot/

GitHub - deepmind/meltingpot: A suite of test scenarios for multi-agent reinforcement learning.

A suite of test scenarios for multi-agent reinforcement learning. - GitHub - deepmind/meltingpot: A suite of test scenarios for multi-agent reinforcement learning.

GitHub
Show threadFarama FoundationApr 25, 2023
For more information, see the full release notes: https://github.com/Farama-Foundation/Shimmy/releases/tag/v1.0.0
Release v1.0.0: Shimmy Becomes Mature 路 Farama-Foundation/Shimmy

Release Notes: We are excited to announce the mature release of Shimmy, an API compatibility tool for converting external RL environments to the Gymnasium and PettingZoo APIs. This allows users to ...

GitHub