ale-py
The Arcade Learning Environment (ALE) - a platform for AI research.
Decision gist · record as of 2026-08-14
Yes, with conditions. ale-py is actively maintained, widely used in RL research, and has no known vulnerabilities. Install it if you are developing RL agents and need a standard Atari benchmark environment. Be aware of the GPL-2.0-only copyleft license if you plan proprietary use, and ensure your Python version is 3.10 or later (free-threaded CPython is not supported).AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.10 or later; free-threaded CPython (e.g., python3.14t) is not supported due to OpenCV wheel compatibility.
- Medium install friction due to compiled wheels for multiple Python versions and platforms; however, prebuilt wheels are available for modern Python (3.10–3.14) on macOS, Linux, and Windows, reducing build complexity.
- Active maintenance with a recent release.
License · maintenance · safety
GPL-2.0-only (copyleft) — GPL-2.0-only is a copyleft license; any derivative work or modified version must also be distributed under GPL-2.0-only. This may restrict commercial or proprietary use without careful licensing review.
last release 2026-05-30 (76 days) · last repo commit 2026-08-10 · 2,442 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 298,625 downloads/mo, #7,871 on PyPI
Alternatives
Verify before relying
pip install ale-py
from ale_py import ALEInterface, roms
ale = ALEInterface()
ale.loadROM(roms.get_rom_path("breakout"))
ale.reset_game()
reward = ale.act(0)
screen_obs = ale.getScreenRGB()- Whether the included Atari ROMs are legally licensed for your intended use.
- Performance characteristics and typical episode length for different Atari games.
- Exact number of supported Atari 2600 games beyond the stated '100+' threshold.
What it is and what it does
ale-py is a Python wrapper around the Stella Atari 2600 emulator, designed to provide a research-grade platform for developing and benchmarking reinforcement learning agents. It decouples emulation from rendering and sound, enabling fast headless training while also supporting visual output when needed. The package includes Atari ROMs, automatic game-over detection, and score extraction for over 100 games, making it a turnkey environment for RL research without requiring separate ROM management.
The package integrates natively with Gymnasium (the maintained successor to OpenAI Gym), so you can use it either through ale-py's direct ALEInterface API or through Gymnasium's standard environment interface. It also provides a C++-based vectorizer for parallel environment execution and WebAssembly support for browser-based experiments. Runtime dependencies are minimal: only numpy and typing-extensions.
Use it for
- Train deep reinforcement learning agents on Atari games as a standard RL benchmark.
- Benchmark policy gradient or Q-learning algorithms against a large suite of games.
- Develop and test game-playing agents with automatic score tracking and episode termination.
- Run vectorized parallel environments for faster training of multiple Atari game instances.
- Create interactive browser-based RL demos or educational tools via WebAssembly.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, with conditions.
ale-py is actively maintained, widely used in RL research, and has no known vulnerabilities. Install it if you are developing RL agents and need a standard Atari benchmark environment. Be aware of the GPL-2.0-only copyleft license if you plan proprietary use, and ensure your Python version is 3.10 or later (free-threaded CPython is not supported).
Install
ale-py on PyPI
Before you install
Medium install friction due to compiled wheels for multiple Python versions and platforms; however, prebuilt wheels are available for modern Python (3.10–3.14) on macOS, Linux, and Windows, reducing build complexity. Active maintenance with a recent release.
Requires Python 3.10 or later; free-threaded CPython (e.g., python3.14t) is not supported due to OpenCV wheel compatibility.
License in practice
GPL-2.0-only is a copyleft license; any derivative work or modified version must also be distributed under GPL-2.0-only. This may restrict commercial or proprietary use without careful licensing review.
Quickstart
pip install ale-py
from ale_py import ALEInterface, roms
ale = ALEInterface()
ale.loadROM(roms.get_rom_path("breakout"))
ale.reset_game()
reward = ale.act(0)
screen_obs = ale.getScreenRGB()Verify before relying
- Whether the included Atari ROMs are legally licensed for your intended use.
- Performance characteristics and typical episode length for different Atari games.
- Exact number of supported Atari 2600 games beyond the stated '100+' threshold.
Package facts
| License | GPL-2.0-only copyleft |
| Python support | Supports the current Python release >=3.10 |
| Install friction | Medium. Platform-specific wheel |
| Runtime dependencies | 2 packagesnumpytyping-extensions |
| Maintenance | Actively maintained 76 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 298,625 / month, #7,871 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Development Status :: 5 - Production/StableIntended Audience :: Science/ResearchProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Topic :: Scientific/EngineeringTopic :: Scientific/Engineering :: Artificial Intelligence |
Evidence: ale_py-0.12.0-cp310-cp310-macosx_13_0_arm64.whl; ale_py-0.12.0-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; ale_py-0.12.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; ale_py-0.12.0-cp310-cp310-win_amd64.whl; ale_py-0.12.0-cp311-cp311-macosx_13_0_arm64.whl; ale_py-0.12.0-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; ale_py-0.12.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; ale_py-0.12.0-cp311-cp311-win_amd64.whl; ale_py-0.12.0-cp312-cp312-macosx_13_0_arm64.whl; ale_py-0.12.0-cp312-cp312-macosx_26_0_arm64.whl; ale_py-0.12.0-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; ale_py-0.12.0-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; ale_py-0.12.0-cp312-cp312-win_amd64.whl; ale_py-0.12.0-cp313-cp313-macosx_13_0_arm64.whl; ale_py-0.12.0-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; ale_py-0.12.0-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl; ale_py-0.12.0-cp313-cp313-win_amd64.whl; ale_py-0.12.0-cp314-cp314-macosx_13_0_arm64.whl; ale_py-0.12.0-cp314-cp314-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl; ale_py-0.12.0-cp314-cp314-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “atari 2600 emulator python”
- ale-pyale-py provides a Python interface to the Atari 2600 emulator Stella,…
- gymnasiumGymnasium provides a standard Python API for building and testing…
- dopamine-rlDopamine is a research framework for prototyping reinforcement…
Give your agent the search over MCP, or paste the wish link into any chat.
More Scientific/Engineering packages
NumPy provides an N-dimensional array object and a comprehensive suite of mathematical, linear algebra, Fourier transform, and random number functions for scientific computing in Python.
pandas provides fast, flexible data structures (Series and DataFrame) for loading, cleaning, transforming, and analyzing labeled or relational data in Python.
scipy provides numerical algorithms for mathematics, science, and engineering—including optimization, integration, linear algebra, Fourier transforms, signal and image processing, and ODE solvers—built on numpy arrays.
scikit-learn provides a comprehensive Python library for supervised and unsupervised machine learning, including classification, regression, clustering, dimensionality reduction, and model evaluation tools built on NumPy and SciPy.
Install it if you need to train, evaluate, or deploy supervised or unsupervised learning models.
dill extends Python's pickle module to serialize and deserialize a much wider range of Python objects, including functions, lambdas, classes, and interpreter sessions, to byte streams for storage or network transmission.
Multiprocess is an enhanced fork of Python's standard multiprocessing library that uses dill for better serialization, allowing you to spawn processes with a threading-like API and share complex objects between them.
Install it if you use multiprocessing and encounter pickle serialization limits with lambdas or complex objects.
See also gymnasium · pettingzoo · kaggle-environments · ursina · nashpy · arcade-mcp · skrl · Shimmy · TextArena · dolphin-memory-engine