Google DeepMind
Change the repository type filter
All
Repositories list
286 repositories
- OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
- Second Order Optimization and Curvature Estimation with K-FAC in JAX.
- Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
- A library for generative social simulation
- A JAX research toolkit for building, editing, and visualizing neural networks.
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.
- 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.
- Tracking Any Point (TAP)
- Real-time behaviour synthesis with MuJoCo, using Predictive Control
- Benchmarking long-form factuality in large language models. Original code for our paper "Long-form factuality in large language models".
- TensorFlow-based neural network library
- Optax is a gradient processing and optimization library for JAX.
- PIX is an image processing library in JAX, for JAX.
- JAX-based neural network library