# google-deepmind/deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

Repository: https://github.com/google-deepmind/deepmind-research
Canonical: https://ross.abutalabs.com/products/deepmind-research
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2026-06-17T13:51:27+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 88, release rhythm 35, longevity 100
- inputs: {"age_days": 2787, "days_push": 77, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15169, forks 2917 (observed 2026-08-28T04:11:09.318335+00:00)

## What it is
A collection of implementations and illustrative code accompanying DeepMind research publications, spanning reinforcement learning, generative models, graph networks, and scientific applications. It serves as reference material for reproducing and building on published DeepMind research.

## Use cases
- reproduce results from DeepMind papers
- learn how deep reinforcement learning algorithms like DQN are implemented
- experiment with research environments like DeepMind Lab or StarCraft II
- study graph network simulations like meshgraphnets
- explore neural network approaches to scientific problems like plasma control or density functionals

## When to choose
- you want reference implementations tied to specific DeepMind publications
- you are a researcher building on published DeepMind methods
- you want illustrative code for advanced ML research topics

## When to avoid
- you need a production-ready, supported ML library
- you want a stable API with long-term maintenance guarantees
- you need a single coherent framework rather than many independent project folders

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, reinforcement-learning, data-science
- domain: artificial-intelligence, machine-learning, deep-learning, reinforcement-learning
- platform: python, cross-platform
- tags: research-code, deepmind, publications, jupyter-notebooks, reference-implementations, research

## Member repositories
- google-deepmind/deepmind-research (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:09.318335+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 2026-08-29T17:06:34.967023+00:00, confidence not recorded.
  - readme: https://github.com/google-deepmind/deepmind-research (fetched 2026-08-28T04:11:09.318335+00:00, sha d20ab0750f80)
- Data as of 2026-08-30T08:39:29.467469+00:00.