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.
More from Embodied
- 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
- Skild AI trains Unitree G1 to play soccer with 140 years of simulated self-play — Distinct-Question-16 · 2026-09-24
- Deepak Pathak: Earth's Only AGI Came From Billions of Years of Physical Self-Play, and Robots Will Scale It — deepakpathak · 2026-09-24
- π0.5 finetuning on real manufacturing: 1 hour of clean data beat the previous 17 — DominiqueCAPaul · 2026-09-24