google-deepmind Goto Github PK

objecthash-proto

ObjectHash for protocol buffers

offpolicy_selection_eslb

open_spiel

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

open_x_embodiment

opro

official code for "Large Language Models as Optimizers"

optax

Optax is a gradient processing and optimization library for JAX.

pbde

perception_test

pg19

pgmax

Loopy belief propagation for factor graphs on discrete variables in JAX

physical_concepts

pix2act

plplot-ffi

LuaJIT wrapper for PLplot

pushworld

PushWorld: A benchmark for manipulation planning with tools and movable obstacles

pycolab

A highly-customisable gridworld game engine with some batteries included. Make your own gridworld games to test reinforcement learning agents!

pysc2

StarCraft II Learning Environment

randomized_positional_encodings

Randomized Positional Encodings Boost Length Generalization of Transformers

rc-data

Question answering dataset featured in "Teaching Machines to Read and Comprehend

relicv2

reverb

Reverb is an efficient and easy-to-use data storage and transport system designed for machine learning research

rgb_stacking

rlax

robovqa

s6

sam_edge

scalable_agent

A TensorFlow implementation of Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures.

scaling_laws_for_routing

semppl

slim-dataset

Datasets used to train Spatial Language Integrating Model (SLIM) in the ‘Encoding Spatial Relations from Natural Language’ paper.

slowfast_nfnets