--- id: "2026-09-23-skild-physical-self-play-soccer" url: "https://postcutoff.com/e/2026-09-23-skild-physical-self-play-soccer/" as_of: "2026-11-22T13:32:00+01:00" date: "2026-09-23" date_precision: day category: robotics importance: 4 confidence: high status: [Confirmed] sources: 5 editor: human editor human_review: null version: "2026-10-04" --- As of: 2026-11-22 13:32 CET. Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/ Canonical page: https://postcutoff.com/e/2026-09-23-skild-physical-self-play-soccer/ # Skild AI's S1 learns soccer through 140+ years of simulated self-play and transfers to a real humanoid On Sept 23, 2026 Skild AI showed "Physical Self-Play": it post-trained its S1 robot foundation model to play soccer only by playing past versions of itself in NVIDIA Isaac Sim, with scoring as the only reward, over 140+ simulated years. Dribbling, shielding, tackling and getting up after falls emerged without specific rewards, and the policy transferred to a real Unitree G1 humanoid playing against humans. ## Key facts - Announced ~Sept 23, 2026 (some outlets say Sept 22) - Self-play against past versions of itself in NVIDIA Isaac Sim; the only reward was 'score' - 140+ years of simulated play - Emergent skills: dribbling, shielding, tackling, fall recovery; early passing in four-agent games - Transferred to a real Unitree G1 humanoid, playing against humans and robots - Compute, wall-clock time and the sim-to-real recipe were not disclosed; a paper was promised - CEO Deepak Pathak: 'This method scales, and we will scale it.' ## What happened Skild applied AlphaZero-style self-play to a physical, multi-agent sport with a general robot foundation model, and showed zero-shot transfer to hardware. ## Why it matters It suggests self-play can produce complex whole-body skills in robotics without demonstrations or reward shaping. Independent replication and the promised paper are pending. ## Your AI and this story - GPT-6.2 Astra (training cutoff May 2026): 115 days after its cutoff - Claude Opus 5.5 (training cutoff June 2026): 85 days after its cutoff - Gemini 4 Hydrogen (training cutoff March 2026): 176 days after its cutoff - Grok 4.7 (training cutoff May 2026): 115 days after its cutoff ## Sources 1. [Skild AI: Physical Self-Play](https://www.skild.ai/blogs/physical-self-play) (skild.ai, official) 2. [Skild AI on X](https://x.com/SkildAI/status/2102807730331492500) (x.com, official) 3. [Humanoids Daily: Skild AI S1 learns soccer through 140 years of simulated self-play](https://www.humanoidsdaily.com/news/skild-ai-s1-learns-soccer-through-140-years-of-simulated-self-play) (humanoidsdaily.com, press) 4. [Interesting Engineering: Skild AI's robot brain taught itself football](https://interestingengineering.com/videos/skild-ais-robot-brain-taught-itself-football-in-140-simulated-years) (interestingengineering.com, press) 5. [Skild AI video: This robot learned football by playing itself for 140 years](https://www.youtube.com/watch?v=lCDNzEXiloY) (youtube.com, video) ## Changes - 2026-09-29 (filed): Created ## Related - 2026-08-25: [Skild AI's S1 learns 10-minute robot tasks from a single video prompt](https://postcutoff.com/e/2026-08-25-skild-ai-s1/index.md) - Archived: 1 post and 2 videos, listed in https://postcutoff.com/e/2026-09-23-skild-physical-self-play-soccer/index.json