---
title: "Policy Network Diffusion"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.04614v1"
permalink: "https://feed.astralor.com/items/itm_a866de16c06e5bdefb9c577a"
published: "2026-11-03T10:04:34.000Z"
score: 58
channel: "ai"
tags: ["多模态","Policy Network Diffusion","Diffusion","AI-generated","Diffusion-based Conditional Policy","Network Parameter Generation","DPPG"]
---

# Policy Network Diffusion

## 速览

Diffusion models have shown remarkable progress in AI-generated content, including images and videos. In this paper, we explore whether diffusion models can generate the parameters of policy networks in reinforcement le…

## 关键点

- Diffusion models have shown remarkable progress in AI-generated content, including images and videos.
- In this paper, we explore whether diffusion models can generate the parameters of policy networks in reinforcement learning (RL), and whether the generated policies exhibit generalization capabilities.
- To achieve this, we propose Diffusion-based Conditional Policy Network Parameter Generation (DPPG), which consists of a Transformer-based autoencoder and a task-conditioned diffusion model.

## 全文

Diffusion models have shown remarkable progress in AI-generated content, including images and videos. In this paper, we explore whether diffusion models can generate the parameters of policy networks in reinforcement learning (RL), and whether the generated policies exhibit generalization capabilities. To achieve this, we propose Diffusion-based Conditional Policy Network Parameter Generation (DPPG), which consists of a Transformer-based autoencoder and a task-conditioned diffusion model. The autoencoder achieves a high compression rate by patchifying network parameters, while the task-conditioned diffusion model generates corresponding parameters conditioned on different environments. Our experiments demonstrate that, with a single unified DPPG model, we can synthesize high-quality policies across a diverse set of tasks from different environment domains, including Classic Control, Atari games, and MuJoCo. Additionally, our method can generate networks with a larger number of parameters compared to previous approaches. Furthermore, we find that in previously unseen environments, DPPG can generate parameters that achieve faster convergence and reach competitive performance, showcasing the potential future applications of parameter generation via diffusion.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_a866de16c06e5bdefb9c577a