# Diffusion Policy: Visuomotor Policy Learning via Action
Source: https://savrn.com/papers/diffusion-policy-visuomotor-policy-learning-via-action-diffusion
Markdown alternate of the page above; the site index is https://savrn.com/llms.txt

---

## Abstract

This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot's visuomotor policy as a conditional denoising diffusion process. We benchmark Diffusion Policy across 11 different tasks from 4 different robot manipulation benchmarks and find that it consistently outperforms existing state-of-the-art robot learning methods with an average improvement of 46.9%. Diffusion Policy learns the gradient of the action-distribution score function and iteratively optimizes with respect to this gradient field during inference via a series of stochastic Langevin dynamics steps. We find that the diffusion formulation yields powerful advantages when used for robot policies, including gracefully handling multimodal action distributions, being suitable for high-dimensional action spaces, and exhibiting impressive training stability. To fully unlock the potential of diffusion models for visuomotor policy learning on physical robots, this paper presents a set of key technical contributions including the incorporation of receding horizon control, visual conditioning, and the time-series diffusion transformer. We hope this work will help motivate a new generation of policy learning techniques that are able to leverage the powerful generative modeling capabilities of diffusion models. Code, data, and training details will be publicly available.

[Full paper on arXiv](https://arxiv.org/abs/2303.04137) · [Code](https://github.com/https://github.com/real-stanford/diffusion_policy)

## Details

arXiv identifier

2303.04137

Published

2023-03-07

Authors

Cheng Chi, Siyuan Feng, Yilun Du, Zhenjia Xu, Eric Cousineau, Benjamin Burchfiel, Shuran Song

## Open Models Built on This Paper

Every model in the SAVRN Model Hub whose card cites this paper, most downloaded first, with what it takes to run each one.

| Model | Task | Size | License | Monthly downloads | Cheapest setup at 16-bit |
| --- | --- | --- | --- | --- | --- |
| [diffusion_pusht](https://savrn.com/models/diffusion-pusht) LeRobot | [Robotics](https://savrn.com/models/tasks/robotics) | 263M | apache-2.0 | 2.8k | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) $1.85/hr |
| [select_block_dp_octe_2stage_4096](https://savrn.com/models/select-block-dp-octe-2stage-4096) Testing | [Robotics](https://savrn.com/models/tasks/robotics) | 266M | apache-2.0 | — | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) $1.85/hr |
| [latest_fold_diffusion_towel_fold2_20261002](https://savrn.com/models/latest-fold-diffusion-towel-fold2-20261002) Yuval Gotlib | [Robotics](https://savrn.com/models/tasks/robotics) | 263M | apache-2.0 | — | 1x [MI300X](https://savrn.com/ai-index/pricing/gpus/mi300x) $1.85/hr |

## Explore More

- [All research papers](https://savrn.com/papers)
- [The model directory](https://savrn.com/models)
- [Datasets](https://savrn.com/datasets)

## Source

- arXiv metadata, read 2026-10-03.
- [How the hub is built](https://savrn.com/model-hub/methodology)