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'.
A TensorFlow implementation of the Differentiable Neural Computer, which accompanies our Nature paper 'Hybrid computing using a neural network with dynamic external memory'.
This notebook is a demo for the BigGAN generators available on TF Hub.
Importance Weighted Actor-Learner Architectures
This repository contains an implementation of "Importance Weighted Actor-Learner Architectures", along with a dynamic batching module.
Graph Nets library
Graph Nets is DeepMind's library for building graph networks in TensorFlow and Sonnet.
A library of reinforcement learning building blocks.
Sonnet is a high level library to build complex neural network structures 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.
Symplectic Gradient Adjustment
This colab implements the Symplectic Gradient Adjustment (SGA) algorithm.
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.
Colab UI Library - TsWidgets
A tool to convert from TypeScript custom element class to UI Widget classes in other languages.
A highly-customisable gridworld game engine with some batteries included, useful for discovering and testing reinforcement learning agent capabilities on small problems.
Multi-Task Self-Supervised ResNet V2
A vision network trained via large-scale multi-task self-supervised learning
Interval Bound Propagation
This repository contains a simple implementation of Interval Bound Propagation (IBP) using TensorFlow.
ShapeGuard is a tool to help with handling shapes in TensorFlow.
Convolutional neural network model for video classification trained on the Kinetics dataset.