Learning algorithms for mean field optimal control
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917966477524992 |
|---|---|
| author | Soner, H. Mete Teichmann, Josef Yan, Qinxin |
| author_facet | Soner, H. Mete Teichmann, Josef Yan, Qinxin |
| contents | We analyze an algorithm to numerically solve the mean-field optimal control problems by approximating the optimal feedback controls using neural networks with problem specific architectures. We approximate the model by an $N$-particle system and leverage the exchangeability of the particles to obtain substantial computational efficiency. In addition to several numerical examples, a convergence analysis is provided. We also developed a universal approximation theorem on Wasserstein spaces. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17869 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning algorithms for mean field optimal control Soner, H. Mete Teichmann, Josef Yan, Qinxin Optimization and Control 35Q89, 35D40, 49L25, 60G99 We analyze an algorithm to numerically solve the mean-field optimal control problems by approximating the optimal feedback controls using neural networks with problem specific architectures. We approximate the model by an $N$-particle system and leverage the exchangeability of the particles to obtain substantial computational efficiency. In addition to several numerical examples, a convergence analysis is provided. We also developed a universal approximation theorem on Wasserstein spaces. |
| title | Learning algorithms for mean field optimal control |
| topic | Optimization and Control 35Q89, 35D40, 49L25, 60G99 |
| url | https://arxiv.org/abs/2503.17869 |