google-deepmind Goto Github PK

dm_hamiltonian_dynamics_suite

dm_hard_eight

dm_memorytasks

A set of 13 diverse machine-learning tasks that require memory to solve.

dm_nevis

NEVIS'22: Benchmarking the next generation of never-ending learners

dm_pix

PIX is an image processing library in JAX, for JAX.

dm_robotics

Libraries, tools and tasks created and used at DeepMind Robotics.

dnc

A TensorFlow implementation of the Differentiable Neural Computer.

dqn

Lua/Torch implementation of DQN (Nature, 2015)

dqn_zoo

DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (DQN) agent.

dramatron

Dramatron uses large language models to generate coherent scripts and screenplays.

dsprites-dataset

Dataset to assess the disentanglement properties of unsupervised learning methods

dynamic-kanerva-machines

This is a self-contained memory module for the Dynamic Kanerva Machine, as reported in the NIPS 2018 paper: Learning Attractor Dynamics for Generative Memory.

eddict

educational

eigengame

Open source code for EigenGame.

einshape

emergent_communication_at_scale

emergent_in_context_learning

emotions_courtship

enn

enn_acme

envlogger

A tool for recording RL trajectories.

fancyflags

A Python library for defining flat or nested dictionary flags.

ferminet

An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations

flows_for_atomic_solids

functa

geomatch

gnn_single_rigids

gqn-datasets

Datasets used to train Generative Query Networks (GQNs) in the ‘Neural Scene Representation and Rendering’ paper.

graphcast