Skild's robot footballer: 140 years of self-play, each version facing a tougher self
deepakpathak · x · 2026-09-24
Skild AI's football-playing robot was trained via self-play: roughly 140 years of simulated experience, with each model version facing a progressively tougher version of itself.
The commentator notes self-play works incredibly well when the rules are fixed and known — roughly true for football physics — but becomes far less predictable in unstructured, chaotic environments. A neat proof that simulation-based training delivers.
More from Embodied
- Guava distills GPT-5.4 into a 4B robot agent with just 2,000 simulated trajectories — jbhuang0604 · 2026-11-09
- Dex-One2Many learns dexterous manipulation from one human video, 95%+ success across 4 hands — jbhuang0604 · 2026-11-09
- Fly-by-Code: coding agents pilot drones via active visual and physical feedback loops — jbhuang0604 · 2026-11-09
- μ0 world model learns robot physics from video only, beats π0 by 5 points on RoboCasa365 — jbhuang0604 · 2026-11-09
- NVIDIA unveils GR00T 2 open-world robot action model, hitting 95% success with 5 demos — CyberRobooo · 2026-11-09
- CoRL keynote to explore open-source data and hardware for robotics — micoolcho · 2026-11-09