Sports Hub

Theo Moore-Calters Vijay Sundaram
🎮 Interactive Demo
GitHub GitHub GitHub




Sports Hub Overview

SportsHub is a simple collection of locomotion MJX environments designed for end-to-end Reinforcement Learning.

  • Built for simplicity
  • Powered by Brax (a well-respected JAX-based RL training framework)
  • Each environment can be viewed live online using the 🚀 Sports Hub  link

Our Research Agents

Humanoid Model

  • Actuators: 17
  • Degrees of Freedom: 24
  • Locomotion observation shape: 276
    • Joint positions: 22
    • Joint velocities: 23
    • Inertia on each body: 170
    • Global velocities on each body: 78
    • Actuator forces: 23

Quadruped Model

  • Actuators: 12
  • Degrees of Freedom: 15
  • Locomotion observation shape: 27
    • Joint positions: 13
    • Joint velocities: 14
We have a catalogue of environments for you to try out, from sprints to long jump, hurdles, fetch tasks, and more; all designed to push the boundaries of agile locomotion and control.

Locomotion

teaser


Loco-Manipulation

teaser

Live Simulation Environments Available at 🚀 Sports Hub

Fetch policy by Quadruped
Fetch policy by Humanoid
Hurdle policy by Humanoid
Gaps policy by Humanoid
Long Jump policy by Humanoid
Long Jump policy by Quadruped
Sprint policy by Humanoid
Sprint policy by Quadruped