{"library":"mujoco-mjx","title":"MuJoCo XLA (MJX)","description":"MJX is a JAX-based physics engine that accelerates MuJoCo simulations on GPU/TPU. It provides differentiable physics for reinforcement learning and robotics. Current version: 3.8.0. Released ~quarterly alongside MuJoCo.","language":"python","status":"active","last_verified":"Fri May 01","install":{"commands":["pip install mujoco-mjx"],"cli":null},"imports":["from mujoco_mjx import MjxModel","from mujoco_mjx import step"],"auth":{"required":false,"env_vars":[]},"quickstart":{"code":"import mujoco\nimport mujoco_mjx as mjx\nimport jax.numpy as jnp\n\nxml = \"\"\"\n\n \n \n \n \n \n \n \n\"\"\"\nm = mujoco.MjModel.from_xml_string(xml)\nd = mujoco.MjData(m)\nmjx_model = mjx.put_model(m)\nmjx_data = mjx.put_data(m, d)\n# Step simulation\nfor _ in range(100):\n ctrl = jnp.zeros(m.nu)\n mjx_data = mjx.step(mjx_model, mjx_data, ctrl)\nprint(\"Final position:\", mjx_data.qpos)","lang":"python","description":"Create a simple MuJoCo model, convert to MJX, and simulate with random control.","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}