google-deepmind/deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 10 minutes ago
Added to GitGenius on September 3rd, 2026
Created on January 15th, 2019
Open Issues & Pull Requests: 358 (+0)
GitHub issues: Enabled
Number of forks: 2,914
Total Stargazers: 15,185 (+0)
Total Subscribers: 339 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 12.7 days
Mean response time: 80.4 days
90th percentile: 324.0 days
Tracked items: 36

How this project is maintained

Around half of the issues opened in the past year never receive a reply. 100% of open issues come from outside the core team, so the backlog reflects real-world use rather than internal planning. Only 2% of issues opened in the past year have been closed.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 43
New in 7 days: 0
Closed in 7 days: 0
Avg open age: 669 days
Stale 30+ days: 43
Stale 90+ days: 41

Recent activity

Opened in 7 days: 0
Closed in 7 days: 0
Comments in 7 days: 0
Events in 7 days: 0

Top labels

No label distribution available yet.

Most active issues this week

No issue events were indexed in the last 7 days.

Detailed Description

DeepMind Research is a repository of implementations and illustrative code accompanying DeepMind publications.

The repository serves researchers who want to understand and build upon DeepMind's published work by providing reference implementations, working code examples, and experimental environments. Rather than publishing papers alone, DeepMind releases the actual code used in research alongside the publications, enabling others to reproduce results, verify findings, and extend the work. The repository contains implementations of specific algorithms like Deep Q-Network and Differential Neural Computer, as well as access to research environments such as DeepMind Lab and StarCraft II integration, allowing researchers to experiment in the same settings DeepMind used.

This repository suits researchers and practitioners who want to study state-of-the-art machine learning and reinforcement learning techniques with working reference implementations. It is particularly valuable for those building on DeepMind's algorithmic contributions or conducting experiments in complex environments. The collection spans multiple research areas and algorithmic approaches, so it functions more as a curated archive of diverse implementations than a single focused tool. Researchers should expect to find code tied to specific papers rather than a unified framework or library.

The project maintains a collection of implementations across different research areas, with code organized around individual publications and research projects. The repository accepts contributions that align with DeepMind's research output and publication strategy.