Google Research

Repositories

• electra

  ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

  nlp deep-learning tensorflow
  Python Apache-2.0 131 1,080 11 2 Updated May 5, 2020

• google-research

  Google Research

  machine-learning research ai
  Jupyter Notebook Apache-2.0 1,812 9,916 95 38 Updated May 5, 2020

• xtreme

  XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 typologically diverse languages and includes nine tasks.
  Shell Apache-2.0 26 210 4 0 Updated May 5, 2020

• tensor2robot

  Distributed machine learning infrastructure for large-scale robotics research
  Python Apache-2.0 54 307 0 1 Updated May 4, 2020

• text-to-text-transfer-transformer

  Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
  Python Apache-2.0 293 2,434 12 4 Updated May 4, 2020

• dex-lang

  Research language for array processing in the Haskell/ML family
  Haskell BSD-3-Clause 20 541 4 1 Updated May 4, 2020

• football

  Check out the new game server:

  reinforcement-learning reinforcement-learning-environments
  Python Apache-2.0 497 2,066 15 (1 issue needs help) 2 Updated May 4, 2020

• batch_rl

  Offline Reinforcement Learning (aka Batch Reinforcement Learning) on Atari 2600 games
  Python Apache-2.0 10 83 0 1 Updated May 3, 2020

• language

  Shared repository for open-sourced projects from the Google AI Language team.

  machine-learning natural-language-processing research
  Python Apache-2.0 143 483 19 0 Updated May 1, 2020

• bert

  TensorFlow code and pre-trained models for BERT

  nlp natural-language-processing google tensorflow natural-language-understanding
  Python Apache-2.0 6,361 22,804 626 71 Updated May 1, 2020

• pegasus
  Python Apache-2.0 3 43 0 0 Updated Apr 30, 2020

• tapas
  Python Apache-2.0 21 147 2 0 Updated Apr 30, 2020

• recsim

  A Configurable Recommender Systems Simulation Platform

  machine-learning google reinforcement-learning simulation tensorflow artificial-intelligence recommender-system
  Python Apache-2.0 56 337 7 0 Updated Apr 30, 2020

• bleurt
  0 2 0 0 Updated Apr 29, 2020

• motion_imitation

  Code accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals"
  Python Apache-2.0 11 108 1 1 Updated Apr 28, 2020

• meta-dataset

  A dataset of datasets for learning to learn from few examples

  benchmark machine-learning tensorflow maml meta-learning few-shot-learning
  Python Apache-2.0 44 232 4 2 Updated Apr 28, 2020

• tf-slim
  Python Apache-2.0 28 75 2 0 Updated Apr 28, 2020

• dads

  Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.

  reinforcement-learning deep-learning unsupervised-learning model-based-rl skill-discovery
  Python Apache-2.0 8 49 0 1 Updated Apr 28, 2020

• cryptanalytic-model-extraction
  0 2 0 0 Updated Apr 23, 2020

• uda

  Unsupervised Data Augmentation (UDA)

  nlp natural-language-processing computer-vision tensorflow cv semi-supervised-learning
  Python Apache-2.0 178 1,125 37 1 Updated Apr 22, 2020

• albert

  ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
  Python Apache-2.0 320 2,011 63 2 Updated Apr 20, 2020

• turkish-morphology

  A two-level morphological analyzer for Turkish.

  nlp natural-language-processing google morphology turkish morphological-analyser natural-language-understanding
  Python Apache-2.0 7 44 1 0 Updated Apr 16, 2020

• rl-reliability-metrics

  The RL Reliability Metrics library provides a set of metrics for measuring the reliability of reinforcement learning (RL) algorithms, as well as statistical tools for comparing algorithms and for computing confidence intervals on these metrics.
  Python Apache-2.0 9 53 0 0 Updated Apr 14, 2020

• dreamer

  Dream to Control: Learning Behaviors by Latent Imagination
  Python Apache-2.0 41 326 1 0 Updated Apr 11, 2020

• sound-separation
  Python Apache-2.0 35 212 3 1 Updated Apr 10, 2020

• morph-net

  Fast & Simple Resource-Constrained Learning of Deep Network Structure

  python machine-learning deep-learning tensorflow automl neural-architecture-search
  Python Apache-2.0 141 885 11 14 Updated Apr 8, 2020

• rigl

  End-to-end training of sparse deep neural networks with little-to-no performance loss.

  machine-learning computer-vision neural-networks sparse-training
  Python Apache-2.0 11 92 0 0 Updated Apr 6, 2020

• augmix

  AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty
  Python Apache-2.0 51 478 2 1 Updated Mar 31, 2020

• realworldrl_suite
  Python Apache-2.0 0 13 0 0 Updated Mar 31, 2020

• seed_rl

  SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.

  impala gcp tf2 rl deepmind-lab atari r2d2
  Python Apache-2.0 53 346 8 0 Updated Mar 27, 2020