arcade-learning-environment

{
  "aliases": [],
  "alternatives": [],
  "build_dependencies": [
    "cmake",
    "ninja"
  ],
  "categories": [],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [
    "numpy",
    "python@3.14",
    "sdl2-compat"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Platform for AI research",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:35:29+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "arcade-learning-environment",
  "github_default_branch": "main",
  "github_last_commit_at": "2026-06-15T17:13:34Z",
  "github_readme_excerpt": "[![Python](https://img.shields.io/pypi/pyversions/ale-py.svg)](https://badge.fury.io/py/ale-py)\n[![PyPI Version](https://img.shields.io/pypi/v/ale-py)](https://pypi.org/project/ale-py)\n\n\u003cp align=\"center\"\u003e\n    \u003ca href=\"https://ale.farama.org/\" target = \"_blank\"\u003e\n    \u003cimg src=\"https://github.com/Farama-Foundation/Arcade-Learning-Environment/blob/main/docs/_static/img/ale.svg\" width=\"500px\" /\u003e\n\u003c/a\u003e\n\n**The Arcade Learning Environment (ALE) is a simple framework that allows researchers and hobbyists to develop AI agents for Atari 2600 games.**\nIt is built on top of the Atari 2600 emulator [Stella](https://stella-emu.github.io) and separates the details of emulation from agent design.\nThis [video](https://www.youtube.com/watch?v=nzUiEkasXZI) depicts over 50 games currently supported in the ALE.\n\nFor an overview of our goals for the ALE read [The Arcade Learning Environment: An Evaluation Platform for General Agents](https://jair.org/index.php/jair/article/view/10819).\nIf you use ALE in your research, we ask that you please cite this paper in reference to the environment. See the [Citing](#Citing) section for BibTeX entries.\n\nFeatures\n--------\n\n- Object-oriented framework with support to add agents and games.\n- Emulation core uncoupled from rendering and sound generation modules for fast emulation with minimal library dependencies.\n- Automatic extraction of game score and end-of-game signal for more than 100  Atari 2600 games.\n- Multi-platform code (compiled and tested under macOS, Windows, and several Linux distributions).\n- Python bindings through [nanobind](https://github.com/wjakob/nanobind).\n- Native support for [Gymnasium](http://github.com/farama-Foundation/gymnasium), the maintained fork of OpenAI Gym.\n- Atari roms are packaged within the pip package.\n- C++ based vectorizer for acting in multiple ROMs at the same time.\n- WebAssembly support for running ALE in the Browser\n\nQuick Start\n===========\n\nThe ALE currently supports three different interfaces: C++, Python, G",
  "github_repo": "Farama-Foundation/Arcade-Learning-Environment",
  "github_stars": 2426,
  "github_topics": [],
  "homepage": "https://github.com/Farama-Foundation/Arcade-Learning-Environment",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 85,
  "installs_365d": 1026,
  "installs_90d": 230,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "GPL-2.0-only",
  "llm_generated_at": null,
  "llm_model": null,
  "name": "arcade-learning-environment",
  "oldnames": [],
  "one_liner": null,
  "optional_dependencies": [],
  "rank_30d": 3708,
  "rank_365d": 3788,
  "rank_90d": 3952,
  "raw_hash": "c1042b5f357a873e",
  "recommended_dependencies": [],
  "revision": 0,
  "ruby_source_path": "Formula/a/arcade-learning-environment.rb",
  "tap": "homebrew/core",
  "test_dependencies": [],
  "uses_from_macos": [],
  "version_head": "HEAD",
  "version_stable": "0.12.0",
  "versioned_formulae": [],
  "why_use_this": null
}