代码库
Open weights language model from Google DeepMind, based on Griffin.
Python
Python
DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (DQN) agent.
Python
Python
Python
Open source code for AlphaFold 2.
Python
GPU-optimized version of the MuJoCo physics simulator, designed for NVIDIA hardware.
Python
mujoco-warpnvidia-warp
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
C++
cppgamesmultiagentpythonreinforcement-learning
Python
weatherweather-forecast
TeX
A suite of test scenarios for multi-agent reinforcement learning.
Python
multiagent-reinforcement-learning
Python
TIPSv2 (CVPR'26) and TIPS (ICLR'25)
Jupyter Notebook
image-textspatial-understandingvision-encoder
Convolutional neural network model for video classification trained on the Kinetics dataset.
Python
TensorFlow-based neural network library
Python
artificial-intelligencedeep-learningmachine-learningneural-networkstensorflow
A collection of formalized statements of conjectures in Lean.
Lean
formal-mathematicslean4
A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.
Python
mujocorobotics
A library of reinforcement learning components and agents
Python
agentsreinforcement-learningresearch
This repository contains implementations and illustrative code to accompany DeepMind publications
Jupyter Notebook
A JAX research toolkit for building, editing, and visualizing neural networks.
Python
fine-tuninginterpretabilityjaxneural-networksvisualization