Dépôts
Dépôts de google-deepmind
Open source code for AlphaFold.
bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
Build Graph Nets in Tensorflow
A customisable 3D platform for agent-based AI research
Learning to Learn in TensorFlow
Multi-Joint dynamics with Contact. A general purpose physics simulator.
A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.
Real-time behaviour synthesis with MuJoCo, using Predictive Control
An open-source library for GPU-accelerated robot learning and sim-to-real transfer.
GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.
Benchmarking physical understanding in generative video models
StarCraft II Learning Environment
TensorFlow-based neural network library