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 8.6k 955

  2. Minari Minari Public

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

    Python 356 51

  3. PettingZoo PettingZoo Public

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

    Python 2.8k 430

  4. Arcade-Learning-Environment Arcade-Learning-Environment Public

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

    C++ 2.2k 437

  5. Gymnasium-Robotics Gymnasium-Robotics Public

    A collection of robotics simulation environments for reinforcement learning

    Python 639 103

  6. Minigrid Minigrid Public

    Simple and easily configurable grid world environments for reinforcement learning

    Python 2.2k 618

Repositories

Showing 10 of 50 repositories
  • MPE2 Public

    A set of communication oriented environments

    Farama-Foundation/MPE2’s past year of commit activity
    Python 1 MIT 5 4 2 Updated Mar 14, 2025
  • PettingZoo Public

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

    Farama-Foundation/PettingZoo’s past year of commit activity
    Python 2,809 430 32 8 Updated Mar 14, 2025
  • farama.org Public
    Farama-Foundation/farama.org’s past year of commit activity
    HTML 2 7 0 0 Updated Mar 14, 2025
  • momaland Public

    Benchmarks for Multi-Objective Multi-Agent Decision Making

    Farama-Foundation/momaland’s past year of commit activity
    Python 83 GPL-3.0 17 2 1 Updated Mar 13, 2025
  • 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
    Python 8,574 MIT 955 60 (1 issue needs help) 10 Updated Mar 13, 2025
  • ViZDoom Public

    Reinforcement Learning environments based on the 1993 game Doom :godmode:

    Farama-Foundation/ViZDoom’s past year of commit activity
    C++ 1,792 413 30 (3 issues need help) 0 Updated Mar 12, 2025
  • stable-retro Public

    Retro games for Reinforcement Learning

    Farama-Foundation/stable-retro’s past year of commit activity
    C 233 MIT 43 12 2 Updated Mar 10, 2025
  • HighwayEnv Public

    A minimalist environment for decision-making in autonomous driving

    Farama-Foundation/HighwayEnv’s past year of commit activity
    Python 2,783 MIT 785 69 7 Updated Mar 10, 2025
  • 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 1,371 MIT 287 10 5 Updated Mar 7, 2025
  • MO-Gymnasium Public

    Multi-objective Gymnasium environments for reinforcement learning

    Farama-Foundation/MO-Gymnasium’s past year of commit activity
    Python 309 MIT 42 2 4 Updated Mar 3, 2025