# google-deepmind/lab

A customisable 3D platform for agent-based AI research

Repository: https://github.com/google-deepmind/lab
Canonical: https://ross.abutalabs.com/products/lab
Language: C
License: NOASSERTION
License Family: other
Topics: machine-learning, artificial-intelligence, neural-networks, deep-learning
Last push: 2023-01-04T15:38:37+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 3563, "days_push": 1337, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 7373, forks 1403 (observed 2026-08-28T04:09:58.573756+00:00)

## What it is
DeepMind Lab is a customisable 3D learning environment built on Quake III Arena (ioquake3) that provides navigation and puzzle-solving tasks for AI agents. It serves as a research testbed, primarily for deep reinforcement learning, with a Python API for agent training.

## Use cases
- train deep reinforcement learning agents in 3D environments
- benchmark navigation and puzzle-solving capabilities of AI agents
- build custom 3D levels and tasks for agent-based AI research
- run a random agent demo to explore the environment API
- evaluate visual navigation and maze-solving in simulated 3D worlds

## When to choose
- you need a challenging 3D testbed for deep RL research
- you want a customisable, open-source game-based learning environment
- you're reproducing or extending published DeepMind Lab experiments

## When to avoid
- you need a modern, actively maintained RL environment
- you require Windows or macOS support (Linux-focused build)
- you want lightweight 2D or low-compute simulation

## Facets
- artifact type: library
- maturity: maintenance
- function: reinforcement-learning, simulation, game-engine, machine-learning
- domain: reinforcement-learning, artificial-intelligence, deep-learning, simulation
- platform: python, cpp, c
- tags: 3d-environment, agent-based-research, quake3, bazel, research-testbed, game-development, linux

## Member repositories
- google-deepmind/lab (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:58.573756+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 2026-08-29T17:38:23.224570+00:00, confidence not recorded.
  - readme: https://github.com/google-deepmind/lab (fetched 2026-08-28T04:09:58.573756+00:00, sha 10a59e349151)
- Data as of 2026-08-30T08:39:29.467469+00:00.