Volume 3, Issue 2
Mean-Field Neural Networks-Based Algorithms for McKean-Vlasov Control Problems

Huyên Pham & Xavier Warin

J. Mach. Learn. , 3 (2024), pp. 176-214.

Published online: 2024-06

[An open-access article; the PDF is free to any online user.]

Export citation
  • Abstract

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 [Pham and Warin, Neural Netw., 168, 2023] 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 stochastic differential equation 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.

  • AMS Subject Headings

  • Copyright

COPYRIGHT: © Global Science Press

  • Email address
  • BibTex
  • RIS
  • TXT
@Article{JML-3-176, author = {Pham , Huyên and Warin , Xavier}, title = {Mean-Field Neural Networks-Based Algorithms for McKean-Vlasov Control Problems}, journal = {Journal of Machine Learning}, year = {2024}, volume = {3}, number = {2}, pages = {176--214}, abstract = {

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 [Pham and Warin, Neural Netw., 168, 2023] 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 stochastic differential equation 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.

}, issn = {2790-2048}, doi = {https://doi.org/10.4208/jml.230106}, url = {http://global-sci.org/intro/article_detail/jml/23211.html} }
TY - JOUR T1 - Mean-Field Neural Networks-Based Algorithms for McKean-Vlasov Control Problems AU - Pham , Huyên AU - Warin , Xavier JO - Journal of Machine Learning VL - 2 SP - 176 EP - 214 PY - 2024 DA - 2024/06 SN - 3 DO - http://doi.org/10.4208/jml.230106 UR - https://global-sci.org/intro/article_detail/jml/23211.html KW - McKean-Vlasov control, Mean-field neural networks, Learning on Wasserstein space, Dynamic programming, Backward SDE. AB -

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 [Pham and Warin, Neural Netw., 168, 2023] 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 stochastic differential equation 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.

Pham , Huyên and Warin , Xavier. (2024). Mean-Field Neural Networks-Based Algorithms for McKean-Vlasov Control Problems. Journal of Machine Learning. 3 (2). 176-214. doi:10.4208/jml.230106
Copy to clipboard
The citation has been copied to your clipboard