Google DeepMind
Change the repository type filter
All
Repositories list
316 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.
- Optax is a gradient processing and optimization library for JAX.
- A library for generative social simulation
- Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.
- A suite of test scenarios for multi-agent reinforcement learning.
- Benchmarking physical understanding in generative video models
- 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.