mjx

A simple JAX-based implementation of random search for locomotion tasks using MuJoCo XLA (MJX).

Highly customizable (and fast) recurrent RL library for JAX/MJX

MyoSuite with MJX (GPU-accelerated) muscle-tendon support

JAX-native robotics: URDF/MJCF import, differentiable MJX dynamics, system identification, calibrated actuators & sensors, whole-body control, and per-unit attested digital twins — one calibrated model from sim to silicon.

Code for the paper "Decentralized neural dynamics and sensory constraints shape brittle star locomotion"

Run JAX and MuJoCo MJX on AMD Ryzen AI MAX (Strix Halo, gfx1151) from pip wheels - no system ROCm - with a hang-safe check that tells you which wheel set works

四足机器人 Go2 全栈控制：Convex MPC · RL（BC/PPO/域随机化）· 混合仲裁，同一套 72 试验推力协议下恢复率 94% —— 全程 CPU 训练，附与代码逐项一致的数学设计文档

TARANTULIN desde Windows con runtime MuJoCo MJX/JAX gestionado en WSL2

Hexapod hardware, MuJoCo/MJX tripod control, and Cartesian residual reinforcement learning

Unitree H1 humanoid walking via DeepMimic-style imitation learning — MuJoCo MJX + JAX, 4096 parallel envs, 9000 FPS, full 19-DOF control against real human mocap data

OpenQuadruped ROS 2 port with MuJoCo/MJX simulation scaffolding

Fork of MuJoCo MPC — adds miniHexa, an 18-DOF hexapod task: real-time MPC to a goal, ported to MJX for RL policy training.

Consolidated MuJoCo and MJX quadruped reinforcement-learning experiments

Simulacion y entrenamiento Sim2Real con MuJoCo MJX, JAX y Brax PPO para Ubuntu nativo y WSL2