Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.18362 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911494637092864 |
|---|---|
| author | Gaby, Nathan Ye, Xiaojing |
| author_facet | Gaby, Nathan Ye, Xiaojing |
| contents | We develop a general theoretical framework for optimal probability density control on standard measure spaces, aimed at addressing large-scale multi-agent control problems. In particular, we establish a maximum principle (MP) for control problems posed on infinite-dimensional spaces of probability distributions and control vector fields. We further derive the Hamilton--Jacobi--Bellman equation for the associated value functional defined on the space of probability distributions. Both results are presented in a concise form and supported by rigorous mathematical analysis, enabling efficient numerical treatment of these problems. Building on the proposed MP, we introduce a scalable numerical algorithm that leverages deep neural networks to handle high-dimensional settings. The effectiveness of the approach is demonstrated through several multi-agent control examples involving domain obstacles and inter-agent interactions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18362 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Maximum Principle of Optimal Probability Density Control Gaby, Nathan Ye, Xiaojing Optimization and Control Artificial Intelligence Machine Learning Numerical Analysis We develop a general theoretical framework for optimal probability density control on standard measure spaces, aimed at addressing large-scale multi-agent control problems. In particular, we establish a maximum principle (MP) for control problems posed on infinite-dimensional spaces of probability distributions and control vector fields. We further derive the Hamilton--Jacobi--Bellman equation for the associated value functional defined on the space of probability distributions. Both results are presented in a concise form and supported by rigorous mathematical analysis, enabling efficient numerical treatment of these problems. Building on the proposed MP, we introduce a scalable numerical algorithm that leverages deep neural networks to handle high-dimensional settings. The effectiveness of the approach is demonstrated through several multi-agent control examples involving domain obstacles and inter-agent interactions. |
| title | Maximum Principle of Optimal Probability Density Control |
| topic | Optimization and Control Artificial Intelligence Machine Learning Numerical Analysis |
| url | https://arxiv.org/abs/2505.18362 |