How ACT works: a robot-learning primer on predicting 100 actions at once

DominiqueCAPaul · x · 2026-09-24

jarothschild published an in-depth explainer of ACT (Tony Zhao et al.) for ML practitioners entering robot learning: why ACT generates the next 100 actions instead of predicting just the next one, and how it works piece by piece. It's the second in his speedrun series; Diffusion Policy comes next week.

Original post →

More from Embodied

Embodied channel →