Skild AI trains a robot to play soccer via 140 years of self-play in a virtual World Cup
deepakpathak · x · 2026-09-24
Robotics company Skild AI unveiled the "#Messinator," a robot trained to play football using large-scale self-play—accumulating the equivalent of 140 years of matches in a virtual World Cup. Deepak Pathak amplified the demo, calling it "Recursive Soccer Intelligence." It's another showcase of multi-agent self-play as a recipe for robot athletic skills.
Related event: Skild AI's Robot Learns Soccer via 140 Years of Simulated Self-Play(13 posts)→
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