Humanoid robot soccer demo: 140 simulated years of self-play training
deepakpathak · x · 2026-09-24
A humanoid robot soccer demo is drawing attention for its difficulty: balance, ball control, collision recovery, opponent modeling, locomotion, and strategy must all run simultaneously.
- The humanoid outputs joint-angle commands 50 times per second, rather than picking from a discrete action space.
- Training involved roughly 140 simulated years — millions of accelerated virtual soccer matches, repeatedly competing against saved earlier versions of its own policy and learning from which actions led to scoring.
- The demo is being called a landmark for embodied multi-skill real-time control.
More from Embodied
- Training real hardware, not a digital twin: learning directly in nonlinear wave systems — bravo_abad · 2026-09-24
- Schmidhuber: No AI robot can match a plumber — screen-world AI isn't true intelligence — SchmidhuberAI · 2026-09-24
- The world is the installed base: the underrated case for humanoid robots — r0ck3t23 · 2026-09-24
- GTSAM 4.3 ships with legged navigation, CUDA-accelerated factor graphs and continuous-time trajectory estimation — fdellaert · 2026-09-24
- Workbench open-sources an agentic lab workspace for hardware engineering on the Ambion kernel — andreisavu · 2026-09-24
- Hugging Face Tutorial: Accelerating Robotics Simulation with NVIDIA Warp and MjWarp — Hugging Face Blog · 2026-09-24