Mean-field neural networks-based algorithms for McKean-Vlasov control problems *
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911801836306432 |
|---|---|
| author | Pham, Huyên Warin, Xavier |
| author_facet | Pham, Huyên Warin, Xavier |
| contents | This paper is devoted to the numerical resolution of McKean-Vlasov control problems via the class of mean-field neural networks introduced in our companion paper [25] in order to learn the solution on the Wasserstein space. We propose several algorithms either based on dynamic programming with control learning by policy or value iteration, or backward SDE from stochastic maximum principle with global or local loss functions. Extensive numerical results on different examples are presented to illustrate the accuracy of each of our eight algorithms. We discuss and compare the pros and cons of all the tested methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_11518 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Mean-field neural networks-based algorithms for McKean-Vlasov control problems * Pham, Huyên Warin, Xavier Optimization and Control Computational Finance Machine Learning This paper is devoted to the numerical resolution of McKean-Vlasov control problems via the class of mean-field neural networks introduced in our companion paper [25] in order to learn the solution on the Wasserstein space. We propose several algorithms either based on dynamic programming with control learning by policy or value iteration, or backward SDE from stochastic maximum principle with global or local loss functions. Extensive numerical results on different examples are presented to illustrate the accuracy of each of our eight algorithms. We discuss and compare the pros and cons of all the tested methods. |
| title | Mean-field neural networks-based algorithms for McKean-Vlasov control problems * |
| topic | Optimization and Control Computational Finance Machine Learning |
| url | https://arxiv.org/abs/2212.11518 |