MuJoCo Playground

Quickstart

Train and visualize a Cartpole policy directly with uvx.

# Train CartpoleBalance (~1 min on CPU)
uvx --default-index https://pypi.org/simple --python 3.13 --from "playground[rl]>=1.0" \
  python -m mujoco_playground.rl.rsl_rl.train \
  --env=CartpoleBalance \
  --logdir=/tmp/rslrl_logs/cartpole_balance \
  --overrides='{"nworld": 64}'

# Play trained policy in MuJoCo Studio web viewer
uvx --default-index https://pypi.org/simple --python 3.13 --from "playground[rl]>=1.0" \
  python -m mujoco_playground.rl.rsl_rl.play \
  --env=CartpoleBalance --resume_path=/tmp/rslrl_logs/cartpole_balance

# Train CartpoleBalance (CUDA 12 driver)
uvx --python 3.13 \
  --index https://download.pytorch.org/whl/cu129 \
  -f https://github.com/NVIDIA/warp/releases/expanded_assets/v1.18.0 \
  --with "warp-lang==1.18.0+cu12" \
  --from "playground[rl]>=1.0" \
  python -m mujoco_playground.rl.rsl_rl.train \
  --env=CartpoleBalance \
  --logdir=/tmp/rslrl_logs/cartpole_balance

# Play trained policy in MuJoCo Studio web viewer
uvx --python 3.13 \
  --index https://download.pytorch.org/whl/cu129 \
  -f https://github.com/NVIDIA/warp/releases/expanded_assets/v1.18.0 \
  --with "warp-lang==1.18.0+cu12" \
  --from "playground[rl]>=1.0" \
  python -m mujoco_playground.rl.rsl_rl.play \
  --env=CartpoleBalance \
  --resume_path=/tmp/rslrl_logs/cartpole_balance

# Train CartpoleBalance (4,096 parallel envs on GPU)
uvx --python 3.13 --from "playground[rl]>=1.0" \
  python -m mujoco_playground.rl.rsl_rl.train \
  --env=CartpoleBalance \
  --logdir=/tmp/rslrl_logs/cartpole_balance

# Play trained policy in MuJoCo Studio web viewer
uvx --python 3.13 --from "playground[rl]>=1.0" \
  python -m mujoco_playground.rl.rsl_rl.play \
  --env=CartpoleBalance \
  --resume_path=/tmp/rslrl_logs/cartpole_balance

What's New in 1.0

MuJoCo Playground 1.0 upgrades the RSS 2025 research preview into a full sim-to-real development toolchain.

Capability	Playground 0.2	Playground 1.0
Framework	JAX	PyTorch
Physics	MJX (JAX or Warp backends)	MuJoCo or MuJoCo Warp
Sim-to-Real	Simulation-only RL gym environments	Sim and real environments with zero switching cost for sim-to-real
Deployment Code	No	Yes
Workflows	RL envs	RL, sim/real teleop, sysid, agentic VLM
Viewer	simulate	Studio (live.mujoco.org)

Robotic Workflows

End-to-end examples connecting simulation and real robot hardware under a shared interface.

Whole-Body Motion Tracking

Large-batch GPU RL training from state and pixels with RSL-RL across control, manipulation, and humanoid motion tracking.

System Identification

Fitting simulated joint dynamics to logged hardware trajectories via mujoco.sysid.

sim

real

Sim & Real Teleoperation

Interactive leader-follower teleoperation in MuJoCo Studio and on physical hardware with foot-pedal episode gating and episodic MCAP trajectory logging.