All Git Users → google-research
103 open source projects by google-research
51. Seed rl
SEED RL: Scalable and Efficient Deep-RL with Accelerated Central Inference. Implements IMPALA and R2D2 algorithms in TF2 with SEED's architecture.
53. Tiny Differentiable Simulator
Tiny Differentiable Simulator is a header-only C++ physics library with zero dependencies.
✭ 513
54. Lasertagger
✭ 491
python56. Meta Dataset
A dataset of datasets for learning to learn from few examples
58. Recsim
A Configurable Recommender Systems Simulation Platform
59. Motion imitation
Code accompanying the paper "Learning Agile Robotic Locomotion Skills by Imitating Animals"
✭ 431
python60. Tensor2robot
Distributed machine learning infrastructure for large-scale robotics research
✭ 388
python61. 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.
✭ 367
shell62. Text To Text Transfer Transformer
Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"
63. Bleurt
BLEURT is a metric for Natural Language Generation based on transfer learning.
✭ 323
python66. Google Research
Google Research
68. Computation Thru Dynamics
Understanding computation in artificial and biological recurrent networks through the lens of dynamical systems.
✭ 273
jupyter-notebook72. dads
Code for 'Dynamics-Aware Unsupervised Discovery of Skills' (DADS). Enables skill discovery without supervision, which can be combined with model-based control.
73. deeplab2
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.
76. mozolm
MozoLM: A language model (LM) serving library
77. rlds
No description, website, or topics provided.
80. mint
Multi-modal Content Creation Model Training Infrastructure including the FACT model (AI Choreographer) implementation.
✭ 285
python85. plur
PLUR (Programming-Language Understanding and Repair) is a collection of source code datasets suitable for graph-based machine learning. We provide scripts for downloading, processing, and loading the datasets. This is done by offering a unified API and data structures for all datasets.
87. recsim ng
RecSim NG: Toward Principled Uncertainty Modeling for Recommender Ecosystems
95. 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.
98. policy-learning-landscape
Explore the optimization landscape for direct policy learning reinforcement learning.
51-100 of 103 user projects