Forget the jargon for a second. Teaching an agent to control a body, real or simulated, directly is hard because the search space of muscle commands is enormous. Motor primitives shrink it: instead of learning every twitch from scratch, the agent learns a small vocabulary of movements and then learns to sequence them.
DeepMind's grant US11403513B2 (issued August 2, 2022) formalizes this with a linear-feedback-stabilized policy, a control trick that keeps the learned movement from flying apart. The CPC tags G06N 3/0472 (recurrent/temporal networks) and G06N 5/00 (knowledge-based methods) reflect that this sits between deep learning and classical control.
Under the hood, linear-feedback-stabilized is the load-bearing phrase. Learned policies can be twitchy and unstable; a feedback term continuously corrects small errors, like a steadying hand. Stabilizing the primitive means the agent can rely on it as a solid building block rather than relearning balance every time.
Why this matters beyond robotics: the primitive-and-recompose pattern is everywhere in modern AI. Language models learn reusable sub-skills and recombine them; agent systems chain learned tools. DeepMind's movement work is a clean, physical instance of a principle, learn modular skills, compose them, that generalizes far past walking.
The careful note: this is a granted patent with claims that set its real scope, and learns to move is a research result, not a shipped product. As a marker it's useful, a dated, named DeepMind grant showing that by 2022, structured movement learning via reusable primitives was core enough to protect.