# Diffusion Policy: Learning Robot Manipulation Policies via Action Diffusion

- Source: Guyuehome
- Published: 2026-11-02T11:16:00.000Z
- RoboHot: https://robohot.news/en/items/szleg5ljiob9s1s4oh4vaq4g2
- Original: https://www.guyuehome.com/detail?id=2104078883591581697

## Summary

Using the Push-T tabletop pushing task as a vehicle, this piece fully reconstructs the mathematical formulation of action diffusion policies, covering cosine-schedule noise addition, the noise-prediction training objective, FiLM conditioning injection, and sliding-window execution. The author also uses public pretrained weights to complete a real inference evaluation across ten seeds.