Grow your team on GitHub
GitHub is home to over 50 million developers working together. Join them to grow your own development teams, manage permissions, and collaborate on projects.
Sign upPinned repositories
Repositories
-
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
-
kapitan
Generic templated configuration management for Kubernetes, Terraform and other things
-
acme
A library of reinforcement learning components and agents
-
graph_nets
Build Graph Nets in Tensorflow
-
dm-haiku
JAX-based neural network library
-
optax
Optax is a gradient processing and optimization library for JAX.
-
reverb
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research
-
lab
A customisable 3D platform for agent-based AI research
-
deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications
-
surface-distance
Library to compute surface distance based performance metrics for segmentation tasks.
-
dm_control
DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
-
sonnet
TensorFlow-based neural network library
-
bsuite
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
-
ferminet
An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations
-
lab2d
A customisable 2D platform for agent-based AI research
-
trfl
TensorFlow Reinforcement Learning
-
jax_verify
Neural network verification in JAX
-
dm_env_rpc
A networking protocol for agent-environment communication
-
dm_env
A Python interface for reinforcement learning environments
-
hanabi-learning-environment
hanabi_learning_environment is a research platform for Hanabi experiments.
-
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.