---
title: "Diffusion Policy: Visuomotor Policy Learning via Action Diffusion"
description: "Diffusion Policy asks how a robot can imitate demonstrations when several incompatible action sequences are all valid. Read it to see how denoising samples one coherent action chunk, why the controller predicts farther than it executes, how that receding horizon corrects drift, and what the reported 46.9% relative improvement, real-robot results, latency, and evaluation protocol actually establish."
canonical_url: "https://fanout.sh/daily/2026-09-24-diffusion-policy-robot-actions"
md_url: "https://fanout.sh/daily/2026-09-24-diffusion-policy-robot-actions.md"
last_updated: "2026-09-24"
access: "public"
---

# Diffusion Policy: Visuomotor Policy Learning via Action Diffusion

Diffusion Policy asks how a robot can imitate demonstrations when several incompatible action sequences are all valid. Read it to see how denoising samples one coherent action chunk, why the controller predicts farther than it executes, how that receding horizon corrects drift, and what the reported 46.9% relative improvement, real-robot results, latency, and evaluation protocol actually establish.

## Paper details

- Authors: Cheng Chi et al.

- Venue: The International Journal of Robotics Research, 2024

- Track: AI Research

- Difficulty: Medium

- Reading time: 35 min

- Original paper: https://doi.org/10.1177/02783649241273668

## What you will learn

- Why averaging demonstrations can create an action that belongs to no successful strategy, while diffusion can sample one mode at a time.

- How observation, prediction, and execution horizons turn a denoised action sequence into a feedback controller.

- How to read the 15-task evaluation, 46.9% relative improvement, real Push-T result, and unresolved inference-step discrepancy without overstating them.

## Continue exploring

[Explore open robotics in Fanout](https://fanout.sh/open-robotics): Connect action diffusion to Fanout's robotics path, where perception, imitation data, control frequency, embodiment, and deployment constraints meet in one physical system.

---
This representation contains public Fanout content only. Protected Pro lessons, account data, billing, checkout, and pricing are not included.

Browse the public content map: https://fanout.sh/sitemap.md