https://playground.mujoco.org/

 MuJoCo Playground

We introduce MuJoCo Playground, a fully open-source framework for
robot learning built with MJX, with the express goal of streamlining
simulation, training, and sim-to-real transfer onto robots. With a
simple installation process (pip install playground), researchers can
train policies in minutes on a single GPU. Playground supports
diverse robotic platforms, including quadrupeds, humanoids, dexterous
hands, and robotic arms, and enables zero-shot sim-to-real transfer
from both state and pixel inputs. This is achieved through an
integrated stack comprising a physics engine, batch renderer, and
training environments. MuJoCo Playground was a community effort
involving multiple groups, and we hope it proves valuable to
researchers and developers alike.

 paper  code  live demo  starter  locomotion  manipulation 
vision
Teaser

Quadruped Locomotion

Joystick

Handstand

Footstand

Fall recovery

Sim2Sim Transfer

Humanoid Locomotion

Manipulation

In-Hand Reorientation

Sim2Sim In-Hand Reorientation

In-Hand Z-Axis Rotation

Vision-based Grasping

ALOHA Peg Insertion

Non-Prehensile Manipulation

All videos on this page are shown at 1x speed (real-time).