Metraipolis › archive › dc_c1eff6579e1a
Policy Network Diffusion — arXiv:2611.04614
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.04614
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-04T18:54:09.264Z
- SHA-256 of the archived text
993016588eaf1e9481c5145225668c82b8c3fae9ddbf5b8f8d6f20fbbdb503e7- Stable URL of this page
https://metraipolis.com/documento/dc_c1eff6579e1a
How to cite
Policy Network Diffusion — arXiv:2611.04614 — arXiv (en), https://arxiv.org/abs/2611.04614 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c1eff6579e1a (Metraipolis archive dc_c1eff6579e1a, sha256 993016588eaf1e9481c5145225668c82b8c3fae9ddbf5b8f8d6f20fbbdb503e7)
BibTeX
@misc{dcc1eff6579e1a,
title = {Policy Network Diffusion — arXiv:2611.04614},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.04614},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c1eff6579e1a; sha256 993016588eaf1e9481c5145225668c82b8c3fae9ddbf5b8f8d6f20fbbdb503e7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04614. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2611.04614 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-04T18:35:37.446Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).