Skild AI trains robots to learn physical skills through self-play

Automatically extracted; no manual editorial approval recorded.

Skild AI has demonstrated a new self-play training approach that enables robots to develop physical skills without relying on human demonstrations, using its S1 robotics foundation model to learn soccer through more than 140 years of simulated play. The company says the technique could eventually allow robots to acquire increasingly complex skills in factories, construction sites, homes and other physical environment

Open source S2

rding to Skild, those capabilities emerged from the objective of scoring rather than from individually engineered rewards for each behavior. After more than 140 years of simulated play, Skild transferred the resulting policy from simulation to a physical humanoid robot and demonstrated it playing soccer. The company says: “We see the successful transfer from simulation to humanoid, along with the sheer complexity of

Open source S5

nipulation and navigation as the number of interacting robots increases. Skild says: “This simulation ran for over a century with a trivial goal. What happens when we run it for orders of magnitude longer, on a virtual construction site, factory, or home?” The research points toward an alternative way of scaling robot learning: using human data and demonstrations to establish broad foundational capabilities, then all

Open source S10

the task, as a bright green flag for self-play on the road to physical AGI.” The work represents a post-training extension of S1, Skild’s robotics foundation model, which the company introduced in August. S1 is pre-trained using data including human videos, glove data, simulation and teleoperation, and is designed to learn tasks from in-context demonstrations. Skild argues, however, that training primarily from human

Open source S6

owing robots to improve those capabilities autonomously through large amounts of simulated experience. If the approach transfers successfully to practical tasks, it could reduce one of the major bottlenecks facing physical AI – the amount of human-generated data required to teach robots increasingly complex behaviors.

Open source S11