From Noise to Control: Parameterized Diffusion Policies
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916068724834304 |
|---|---|
| author | Zhang, Renhao Fu, Haotian Jia, Mingxi Konidaris, George Du, Yilun da Silva, Bruno Castro |
| author_facet | Zhang, Renhao Fu, Haotian Jia, Mingxi Konidaris, George Du, Yilun da Silva, Bruno Castro |
| contents | We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters embedded in a learned behavior manifold. By constructing this manifold so that distances between latent representations reflect the semantic similarity between physical trajectories, we transform diffusion from a mechanism for stochastic diversity into a precise and optimizable tool for behavior steering. Our approach enables smooth interpolation between known strategies and efficient adaptation to novel constraints without updating policy weights. We demonstrate that PDP significantly improves adaptation performance on complex multimodal benchmarks in both simulated and real-robot experiments compared to standard diffusion policies, particularly in scenarios requiring the synthesis of novel behaviors. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2606_00336 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Noise to Control: Parameterized Diffusion Policies Zhang, Renhao Fu, Haotian Jia, Mingxi Konidaris, George Du, Yilun da Silva, Bruno Castro Artificial Intelligence Machine Learning We propose Parameterized Diffusion Policy (PDP), a framework for learning diffusion policies conditioned on low-dimensional, continuous parameters embedded in a learned behavior manifold. By constructing this manifold so that distances between latent representations reflect the semantic similarity between physical trajectories, we transform diffusion from a mechanism for stochastic diversity into a precise and optimizable tool for behavior steering. Our approach enables smooth interpolation between known strategies and efficient adaptation to novel constraints without updating policy weights. We demonstrate that PDP significantly improves adaptation performance on complex multimodal benchmarks in both simulated and real-robot experiments compared to standard diffusion policies, particularly in scenarios requiring the synthesis of novel behaviors. |
| title | From Noise to Control: Parameterized Diffusion Policies |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2606.00336 |