Pinned repositories
Repositories
-
open_spiel
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
-
dm_env
A Python interface for reinforcement learning environments
-
acme
A library of reinforcement learning components and agents
-
reverb
Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research
-
dm-haiku
JAX-based neural network library
-
lab2d
A customisable 2D platform for agent-based AI research
-
lab
A customisable 3D platform for agent-based AI research
-
deepmind-research
This repository contains implementations and illustrative code to accompany DeepMind publications
-
optax
Optax is a gradient processing and optimization library for JAX.
-
ferminet
An implementation of the Fermionic Neural Network for ab-initio electronic structure calculations
-
dm_alchemy
DeepMind Alchemy task environment: a meta-reinforcement learning benchmark
-
tree
tree is a library for working with nested data structures
-
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.
-
dm_env_rpc
A networking protocol for agent-environment communication
-
bsuite
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
-
labmaze
A standalone release of DeepMind Lab's maze generator with Python bindings.
-
fancyflags
A Python library for defining flat or nested dictionary flags.
-
jraph
A Graph Neural Network Library in Jax
-
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.
-
sonnet
TensorFlow-based neural network library
-
tensor_annotations
Annotating tensor shapes using Python types
-
gqn-datasets
Datasets used to train Generative Query Networks (GQNs) in the ‘Neural Scene Representation and Rendering’ paper.
-
multidim-image-augmentation Archived
This package provides TensorFlow Ops for multidimensional volumetric image augmentation.
-
dm_memorytasks
A set of 13 diverse machine-learning tasks that require memory to solve.
-
hanabi-learning-environment
hanabi_learning_environment is a research platform for Hanabi experiments.
