# google-research/football

Check out the new game server:

Repository: https://github.com/google-research/football
Canonical: https://ross.abutalabs.com/products/football
Homepage: https://research-football.dev
Language: Python
License: Apache-2.0
License Family: permissive
Topics: reinforcement-learning, reinforcement-learning-environments
Archived: true
Last push: 2025-06-17T08:34:25+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 27, release rhythm 8, longevity 100
- inputs: {"age_days": 2648, "days_push": 442, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3661, forks 1380 (observed 2026-08-28T04:08:13.299028+00:00)

## What it is
Google Research Football is a reinforcement learning environment based on the open-source Gameplay Football game, created by the Google Brain team. It provides a football simulation where RL agents can be trained, runnable locally, via Docker, or in Colab.

## Use cases
- train reinforcement learning agents to play football
- benchmark RL algorithms on a simulated sports environment
- run RL research experiments in a game environment
- participate in Kaggle football RL competitions
- learn RL by training agents in a game simulator

## When to choose
- you need a rich, physics-based RL environment for research
- you want to train agents on a complex multi-agent game
- you want a quick-start RL environment via Colab or Docker

## When to avoid
- you need a lightweight or fast-to-step RL environment
- you need a non-game or non-simulation domain
- you need commercial-grade game rendering or production gameplay

## Facets
- artifact type: library
- maturity: maintenance
- function: reinforcement-learning, simulation, game-engine
- domain: reinforcement-learning, machine-learning
- platform: windows, python
- tags: rl-environment, football-simulation, google-brain, gym-environment, research-environment, game-development, research, linux, macos, docker

## Member repositories
- google-research/football (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:13.299028+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 2026-08-29T18:31:35.113704+00:00, confidence not recorded.
  - readme: https://github.com/google-research/football (fetched 2026-08-28T04:08:13.299028+00:00, sha f8b6cddd0f31)
- Data as of 2026-08-30T08:39:29.467469+00:00.