DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Python 2.9k 541
TensorFlow-based neural network library
Python 9.3k 1.3k
This repository contains implementations and illustrative code to accompany DeepMind publications
Jupyter Notebook 10.6k 2.2k
A library of reinforcement learning components and agents
Python 2.7k 343
JAX-based neural network library
Python 2.1k 159
Open source code for AlphaFold.
Python 8.8k 1.5k
Multi-framework implementation of Deep Kernel Shaping and Tailored Activation Transformations, which are methods that modify neural network models (and their initializations) to make them easier to train.
Multi-Joint dynamics with Contact. A general purpose physics simulator.
A suite of test scenarios for multi-agent reinforcement learning.
PIX is an image processing library in JAX, for JAX.
Optax is a gradient processing and optimization library for JAX.
