MuJoCo Playground 1.0 ships full sim-to-real workflows with SO101 and YAM robots supported out of the box

philfung · x · 2026-11-10

Google DeepMind released MuJoCo Playground 1.0, an open-source suite of robot environments for end-to-end simulation and hardware workflows.

• Sim-to-real out of the box: no longer just RL in sim — SO101 and YAM robots are supported in both sim and real hardware
• Design: decouples robot and sensor logic from plain task logic, making sim-to-real with MuJoCo more seamless, from large-batch RL and zero-shot sim-to-real to agentic harness development
• Deeply integrated with MuJoCo, MuJoCo Warp, MuJoCo Studio, and reaf-sim
• Low barrier to entry: quickstart commands let you train a CartpoleBalance policy in 1 minute on CPU via uvx and replay it in the MuJoCo Studio web viewer; CUDA 12/13 GPU training commands included

Repo: github.com/google-deepmind/mujocoplayground

Original post →

More from Embodied

• Developer uses a 1.9B decision model on a laptop to flag dirty restaurant tables in real time — JosephJacks_ · 2026-11-10
• Fable 5.2 beats specialized robotics AI on dual-arm RoboDojo benchmark — FinanceYF5 · 2026-11-10
• LingBot-Touch 开源触觉基础模型：近 5000 小时真实数据预训练 — dair_ai · 2026-11-10
• Norway runs 2,000+ underwater AI laser robots delousing 50 million salmon around the clock — cephaloform · 2026-11-10
• Anthropic robotics model drop: bitter lesson may hold in robotics — beffjezos · 2026-11-10
• Rider shares first-person Cybercab experience: skipping downtown driving in Austin — yunta_tsai · 2026-11-10

Embodied channel →