Open Source Code


Source code of DQN 3.0, a Lua-based deep reinforcement learning architecture for reproducing the experiments described in our Nature paper 'Human-level control through deep reinforcement learning'.

View publication • View source on GitHub


A TensorFlow implementation of the Differentiable Neural Computer, which accompanies our Nature paper 'Hybrid computing using a neural network with dynamic external memory'.

View publication • Blog post •  View source on GitHub


This notebook is a demo for the BigGAN generators available on TF Hub.

View paper • View notebook

Importance Weighted Actor-Learner Architectures

This repository contains an implementation of "Importance Weighted Actor-Learner Architectures", along with a dynamic batching module.

View paper • View source on GitHub

Graph Nets library

Graph Nets is DeepMind's library for building graph networks in TensorFlow and Sonnet.

View paper • View source on GitHub


A library of reinforcement learning building blocks.

View blog post • View source on GitHub

DeepMind Sonnet

Sonnet is a high level library to build complex neural network structures in TensorFlow. 

Blog post • View source on GitHub

L2L in TensorFlow

Learning to Learn (L2L) is a TensorFlow implementation of 'Learning to learn by gradient descent by gradient descent', a fully differentiable approach which learns optimization algorithms by optimizing them.

View publication • View source on GitHub


Code for the StreetLearn environment, for academic research into navigating cities without a map.

Website • View source on GitHub • Blog post

Symplectic Gradient Adjustment

This colab implements the Symplectic Gradient Adjustment (SGA) algorithm.

View paper • View source on GitHub

Conditional Neural Processes

Aa notebook implementation of Conditional Neural Processes (CNPs) that can be run in the browser, with an overview of the different building blocks of the model and the code to run it.

View paper • View source on GitHub

Colab UI Library - TsWidgets

 A tool to convert from TypeScript custom element class to UI Widget classes in other languages.

View source on GitHub


A highly-customisable gridworld game engine with some batteries included, useful for discovering and testing reinforcement learning agent capabilities on small problems.

View source on GitHub

Multi-Task Self-Supervised ResNet V2

A vision network trained via large-scale multi-task self-supervised learning

View publication • View source on GitHub

Interval Bound Propagation

This repository contains a simple implementation of Interval Bound Propagation (IBP) using TensorFlow.

View paper • View source on GitHub


ShapeGuard is a tool to help with handling shapes in TensorFlow.

View source on GitHub

I3D model

Convolutional neural network model for video classification trained on the Kinetics dataset.

View publication • View source on GitHub