Brax is a fast and fully differentiable physics engine for large-scale rigid body simulations, built on JAX. It is designed for research in reinforcement learning and robotics, enabling efficient simulations and gradient-based optimization.
Features
- GPU/TPU-accelerated physics simulations using JAX
- Fully differentiable physics engine for gradient-based learning
- Includes environments for RL benchmarks like humanoids and quadrupeds
- Supports batched parallel simulations for high efficiency
- Integrates seamlessly with reinforcement learning frameworks
License
Apache License V2.0Follow Brax
Other Useful Business Software
Go From AI Idea to AI App Fast
Access Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Brax!