DeepMind

Repositories

• kapitan

  Generic templated configuration management for Kubernetes, Terraform and other things

  python docker kubernetes devops aws-kms jinja2 terraform
  Python 120 1,192 45 (6 issues need help) 9 Updated Jun 4, 2020

• dm-haiku

  JAX-based neural network library

  machine-learning deep-neural-networks deep-learning neural-networks jax
  Python Apache-2.0 41 593 6 3 Updated Jun 4, 2020

• acme

  A library of reinforcement learning components and agents
  Python Apache-2.0 46 751 0 0 Updated Jun 4, 2020

• reverb

  Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research
  C++ Apache-2.0 8 122 1 0 Updated Jun 4, 2020

• graph_nets

  Build Graph Nets in Tensorflow

  deep-learning tensorflow graphs artificial-intelligence neural-networks sonnet graph-networks
  Python Apache-2.0 655 4,379 7 2 Updated Jun 3, 2020

• tree

  tree is a library for working with nested data structures
  Python Apache-2.0 7 73 3 0 Updated Jun 3, 2020

• dm_env

  A Python interface for reinforcement learning environments

  python api machine-learning reinforcement-learning deep-learning interface
  Python Apache-2.0 16 67 0 1 Updated Jun 3, 2020

• deepmind-research

  This repository contains implementations and illustrative code to accompany DeepMind publications
  Jupyter Notebook Apache-2.0 386 1,445 7 3 Updated Jun 2, 2020

• open_spiel

  OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.

  python swift games reinforcement-learning cpp multiagent
  C++ Apache-2.0 418 2,185 14 6 Updated Jun 2, 2020

• spriteworld

  Spriteworld: a flexible, configurable python-based reinforcement learning environment

  environment sprites procedural rl deepmind generative
  Python Apache-2.0 40 310 0 0 Updated Jun 1, 2020

• bsuite

  bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
  Python Apache-2.0 119 993 1 0 Updated May 29, 2020

• dm_control

  The DM Control Suite and Package is a tool for developing and testing reinforcement learning agents for the MuJoCo physics engine.

  machine-learning reinforcement-learning deep-learning artificial-intelligence neural-networks physics-simulation mujoco
  Python Apache-2.0 314 1,850 16 0 Updated May 20, 2020

• sonnet

  TensorFlow-based neural network library

  machine-learning deep-learning tensorflow artificial-intelligence neural-networks
  Python Apache-2.0 1,210 8,361 9 1 Updated May 14, 2020

• pysc2

  StarCraft II Learning Environment

  machine-learning reinforcement-learning starcraft-ii-replays starcraft-ii blizzard-api deepmind
  Python Apache-2.0 1,043 6,879 31 (3 issues need help) 7 Updated May 14, 2020

• dm_env_rpc

  A networking protocol for agent-environment communication
  Python Apache-2.0 1 15 0 0 Updated May 7, 2020

• rlax
  Python Apache-2.0 27 394 0 0 Updated May 1, 2020

• lamb

  LAnguage Modelling Benchmarks
  Python Apache-2.0 11 90 2 1 Updated Apr 23, 2020

• trfl

  TensorFlow Reinforcement Learning
  Python Apache-2.0 358 3,004 2 1 Updated Apr 20, 2020

• multidim-image-augmentation

  This package provides TensorFlow Ops for multidimensional volumetric image augmentation.
  C++ Apache-2.0 15 104 4 1 Updated Apr 20, 2020

• narrativeqa

  This repository contains the NarrativeQA dataset. It includes the list of documents with Wikipedia summaries, links to full stories, and questions and answers.
  Shell Apache-2.0 56 367 0 0 Updated Apr 15, 2020

• mc_gradients
  Jupyter Notebook Apache-2.0 14 74 0 0 Updated Apr 9, 2020

• dm_memorytasks

  A set of 13 diverse machine-learning tasks that require memory to solve.
  Python Apache-2.0 7 143 0 0 Updated Apr 7, 2020

• neural-processes

  This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).
  Jupyter Notebook Apache-2.0 114 638 2 4 Updated Mar 20, 2020

• xquad
  6 52 1 0 Updated Mar 4, 2020

• pg19
  Apache-2.0 15 97 1 0 Updated Feb 25, 2020

• ai-safety-gridworlds

  This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents.
  Python Apache-2.0 87 440 0 1 Updated Feb 12, 2020

• wasserstein_fairness

  An implementation of Wasserstein Fair Classification, a conference paper submitted to UAI 2019.

  fairness optimal-transport
  Python Apache-2.0 4 8 0 1 Updated Jan 26, 2020

• leaps-and-bounds

  This is an implementation of LeapsAndBounds and Structured Procrastination for approximately optimal algorithm configuration.
  Python Apache-2.0 1 6 0 1 Updated Jan 26, 2020

• learning-to-learn

  Learning to Learn in TensorFlow

  machine-learning deep-learning artificial-intelligence neural-networks
  Python Apache-2.0 601 3,976 10 4 Updated Jan 19, 2020

• lab

  A customisable 3D platform for agent-based AI research

  machine-learning deep-learning artificial-intelligence neural-networks
  C GPL-2.0 1,249 6,167 33 2 Updated Jan 7, 2020