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
Build Agents and Models on One Platform
Gemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of Brax!