# openai/roboschool

DEPRECATED: Open-source software for robot simulation, integrated with OpenAI Gym.

Repository: https://github.com/openai/roboschool
Canonical: https://ross.abutalabs.com/products/roboschool
Language: Python
License: NOASSERTION
License Family: other
Archived: true
Last push: 2023-04-02T11:37:04+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3397, "days_push": 1249, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, 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 2169, forks 490 (observed 2026-08-28T04:06:21.594242+00:00)

## What it is
Roboschool is an open-source robot simulation library providing physics-based Gym environments for reinforcement learning research, including locomotion tasks like Humanoid, Hopper, and HalfCheetah. It is officially deprecated and archived, with OpenAI recommending PyBullet as the replacement.

## Use cases
- train reinforcement learning agents on robot locomotion tasks
- simulate humanoid and quadruped robots with OpenAI Gym
- replicate MuJoCo environments without a license
- benchmark RL policies on classic control tasks like inverted pendulum
- run multiplayer robot environments for research

## When to choose
- studying or reproducing historical OpenAI RL research that used Roboschool
- you need the exact legacy environments for comparison

## When to avoid
- starting any new robotics or RL simulation project
- you need maintained software or bug fixes
- you want modern physics simulation features - use PyBullet instead

## Facets
- artifact type: library
- maturity: abandoned
- function: simulation, machine-learning, reinforcement-learning, game-engine
- domain: robotics, reinforcement-learning, simulation, machine-learning
- platform: python
- tags: openai-gym, robot-simulation, physics-simulation, deprecated, mujco-alternative, bullet-physics, linux, macos

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

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:21.594242+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 2026-08-30T02:49:27.914597+00:00, confidence not recorded.
  - readme: https://github.com/openai/roboschool (fetched 2026-08-28T04:06:21.594242+00:00, sha 95deab959aed)
  - registry_pypi: https://pypi.org/pypi/roboschool/json (fetched 2026-08-29T10:29:31.395408+00:00, sha 2102701cb94f)
- Data as of 2026-08-30T08:39:29.467469+00:00.