# alex-petrenko/sample-factory

High throughput synchronous and asynchronous reinforcement learning

Repository: https://github.com/alex-petrenko/sample-factory
Canonical: https://ross.abutalabs.com/products/sample-factory
Homepage: https://samplefactory.dev
Language: Python
License: MIT
License Family: permissive
Topics: reinforcement-learning
Last push: 2026-07-02T18:21:57+00:00

## Health v2 (maintenance only)
Score: 63/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 8, longevity 100
- inputs: {"age_days": 2632, "days_push": 62, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1017, forks 153 (observed 2026-08-28T04:03:14.682159+00:00)

## What it is
Sample Factory is a high-throughput Python reinforcement learning library implementing synchronous and asynchronous policy gradient algorithms (PPO/APPO). It supports single- and multi-agent training, self-play, Population-Based Training, and integrates with environments like MuJoCo, Atari, ViZDoom, Isaac Gym, and DeepMind Lab.

## Use cases
- train RL agents with PPO at high throughput
- train multi-agent RL policies with self-play
- train agents in ViZDoom or Isaac Gym environments
- run population-based training for RL experiments
- benchmark RL algorithm throughput on CPU or GPU
- upload trained RL models to the HuggingFace Hub

## When to choose
- you need maximum training throughput for policy gradient RL
- you want synchronous or asynchronous PPO with multi-GPU support
- you need multi-agent training, self-play, or PBT
- you want a library designed to be imported with custom environments as first-class citizens

## When to avoid
- you need Windows support
- you need off-policy algorithms like SAC or DQN
- you want a simple high-level API over many algorithm families rather than a focused PPO implementation

## Facets
- artifact type: library
- maturity: active
- function: reinforcement-learning, machine-learning, gpu-computing, benchmarking
- domain: reinforcement-learning, machine-learning, artificial-intelligence, robotics
- platform: python
- tags: ppo, appo, policy-gradient, multi-agent, self-play, population-based-training, vizdoom, isaacgym, mujoco, atari, huggingface, game-development, linux, macos, gpu

## Member repositories
- alex-petrenko/sample-factory (main) score 63

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:14.682159+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 2026-08-30T07:11:10.516314+00:00, confidence not recorded.
  - readme: https://github.com/alex-petrenko/sample-factory (fetched 2026-08-28T04:03:14.682159+00:00, sha 1cb883061edc)
  - homepage: https://samplefactory.dev (fetched 2026-08-29T13:10:12.638769+00:00, sha c2a2d835dcc1)
  - site_page: https://www.samplefactory.dev/01-get-started/installation (fetched 2026-08-29T13:10:12.700486+00:00, sha f2101f1d86b6)
  - registry_pypi: https://pypi.org/pypi/sample-factory/json (fetched 2026-08-29T13:10:12.716258+00:00, sha 40b346f90d71)
  - site_page: https://www.samplefactory.dev/05-troubleshooting/troubleshooting (fetched 2026-08-29T13:10:12.702733+00:00, sha 855713ed7b5a)
  - site_page: https://www.samplefactory.dev/09-environment-integrations/mujoco (fetched 2026-08-29T13:10:12.704681+00:00, sha fef68043d234)
  - site_page: https://www.samplefactory.dev/09-environment-integrations/atari (fetched 2026-08-29T13:10:12.706682+00:00, sha cdc8822ab0a6)
  - site_page: https://www.samplefactory.dev/09-environment-integrations/vizdoom (fetched 2026-08-29T13:10:12.708842+00:00, sha 09d994aea909)
  - site_page: https://www.samplefactory.dev/09-environment-integrations/dmlab (fetched 2026-08-29T13:10:12.710720+00:00, sha 17179089e5b1)
  - site_page: https://www.samplefactory.dev/09-environment-integrations/megaverse (fetched 2026-08-29T13:10:12.712607+00:00, sha 62f7972d535e)
- Data as of 2026-08-30T08:39:29.467469+00:00.