Skip to content
@Farama-Foundation

Farama Foundation

The Farama foundation is a nonprofit organization working to develop and maintain open source reinforcement learning tools.

Pinned Loading

  1. Gymnasium Gymnasium Public

    An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

    Python 7.3k 813

  2. Minari Minari Public

    A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

    Python 289 43

  3. PettingZoo PettingZoo Public

    An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

    Python 2.6k 412

  4. Shimmy Shimmy Public

    An API conversion tool for popular external reinforcement learning environments

    Python 139 20

  5. Minigrid Minigrid Public

    Simple and easily configurable grid world environments for reinforcement learning

    Python 2.1k 609

  6. Gymnasium-Robotics Gymnasium-Robotics Public

    A collection of robotics simulation environments for reinforcement learning

    Python 560 89

Repositories

Showing 10 of 50 repositories
  • Farama-Foundation/farama.org’s past year of commit activity
    HTML 2 7 1 0 Updated Nov 10, 2024
  • Gymnasium Public

    An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

    Farama-Foundation/Gymnasium’s past year of commit activity
  • Minari Public

    A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

    Farama-Foundation/Minari’s past year of commit activity
    Python 289 43 13 3 Updated Nov 7, 2024
  • Arcade-Learning-Environment Public

    The Arcade Learning Environment (ALE) -- a platform for AI research.

    Farama-Foundation/Arcade-Learning-Environment’s past year of commit activity
    C++ 2,170 GPL-2.0 422 34 4 Updated Nov 6, 2024
  • Metaworld Public

    Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

    Farama-Foundation/Metaworld’s past year of commit activity
    Python 1,266 MIT 273 8 5 Updated Nov 6, 2024
  • MAgent2 Public

    An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments

    Farama-Foundation/MAgent2’s past year of commit activity
  • D4RL Public

    A collection of reference environments for offline reinforcement learning

    Farama-Foundation/D4RL’s past year of commit activity
    Python 1,336 Apache-2.0 286 100 8 Updated Nov 3, 2024
  • Minigrid Public

    Simple and easily configurable grid world environments for reinforcement learning

    Farama-Foundation/Minigrid’s past year of commit activity
    Python 2,115 609 23 9 Updated Nov 1, 2024
  • Miniworld Public

    Simple and easily configurable 3D FPS-game-like environments for reinforcement learning

    Farama-Foundation/Miniworld’s past year of commit activity
    Python 700 Apache-2.0 131 2 4 Updated Nov 1, 2024
  • Gymnasium-Robotics Public

    A collection of robotics simulation environments for reinforcement learning

    Farama-Foundation/Gymnasium-Robotics’s past year of commit activity
    Python 560 MIT 89 9 (1 issue needs help) 5 Updated Nov 1, 2024