# openai/gym

A toolkit for developing and comparing reinforcement learning algorithms.

Repository: https://github.com/openai/gym
Canonical: https://ross.abutalabs.com/products/gym
Homepage: https://www.gymlibrary.dev
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2026-03-26T23:13:27+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 74, release rhythm 8, longevity 100
- inputs: {"age_days": 3780, "days_push": 160, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 37251, forks 8682 (observed 2026-08-28T04:12:01.383378+00:00)

## What it is
Gym is a Python toolkit for developing and comparing reinforcement learning algorithms via a standard API between learning algorithms and environments, with a standard set of environments like CartPole and Atari. It is now deprecated: maintenance moved to Gymnasium, a drop-in replacement, and Gym receives no further updates.

## Use cases
- train reinforcement learning agents on standard environments
- benchmark RL algorithms against a common API
- simulate control tasks like CartPole for RL research
- build custom RL environments with a standard interface
- learn reinforcement learning with classic toy environments

## When to choose
- maintaining legacy code that already depends on the gym API
- reading older RL tutorials or papers that use gym

## When to avoid
- starting a new reinforcement learning project (use Gymnasium instead)
- needing bug fixes or new environment features
- requiring official Windows support

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, reinforcement-learning, simulation
- domain: reinforcement-learning, machine-learning, artificial-intelligence, simulation
- platform: python
- tags: reinforcement-learning, environment-api, deprecated, gymnasium-successor, benchmarking-environments, linux, macos

## Member repositories
- openai/gym (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.383378+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:25:38.938137+00:00, confidence not recorded.
  - readme: https://github.com/openai/gym (fetched 2026-08-28T04:12:01.383378+00:00, sha 1a1c28b9e698)
- Data as of 2026-08-30T08:39:29.467469+00:00.