Kernel Expansions for High-Dimensional Mean-Field Control with Non-local Interactions

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Vidal, Alexander, Fung, Samy Wu, Osher, Stanley, Tenorio, Luis, Nurbekyan, Levon
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909206247899136
author Vidal, Alexander
Fung, Samy Wu
Osher, Stanley
Tenorio, Luis
Nurbekyan, Levon
author_facet Vidal, Alexander
Fung, Samy Wu
Osher, Stanley
Tenorio, Luis
Nurbekyan, Levon
contents Mean-field control (MFC) problems aim to find the optimal policy to control massive populations of interacting agents. These problems are crucial in areas such as economics, physics, and biology. We consider the non-local setting, where the interactions between agents are governed by a suitable kernel. For $N$ agents, the interaction cost has $\mathcal{O}(N^2)$ complexity, which can be prohibitively slow to evaluate and differentiate when $N$ is large. To this end, we propose an efficient primal-dual algorithm that utilizes basis expansions of the kernels. The basis expansions reduce the cost of computing the interactions, while the primal-dual methodology decouples the agents at the expense of solving for a moderate number of dual variables. We also demonstrate that our approach can further be structured in a multi-resolution manner, where we estimate optimal dual variables using a moderate $N$ and solve decoupled trajectory optimization problems for large $N$. We illustrate the effectiveness of our method on an optimal control of 5000 interacting quadrotors.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10922
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Kernel Expansions for High-Dimensional Mean-Field Control with Non-local Interactions
Vidal, Alexander
Fung, Samy Wu
Osher, Stanley
Tenorio, Luis
Nurbekyan, Levon
Optimization and Control
Mean-field control (MFC) problems aim to find the optimal policy to control massive populations of interacting agents. These problems are crucial in areas such as economics, physics, and biology. We consider the non-local setting, where the interactions between agents are governed by a suitable kernel. For $N$ agents, the interaction cost has $\mathcal{O}(N^2)$ complexity, which can be prohibitively slow to evaluate and differentiate when $N$ is large. To this end, we propose an efficient primal-dual algorithm that utilizes basis expansions of the kernels. The basis expansions reduce the cost of computing the interactions, while the primal-dual methodology decouples the agents at the expense of solving for a moderate number of dual variables. We also demonstrate that our approach can further be structured in a multi-resolution manner, where we estimate optimal dual variables using a moderate $N$ and solve decoupled trajectory optimization problems for large $N$. We illustrate the effectiveness of our method on an optimal control of 5000 interacting quadrotors.
title Kernel Expansions for High-Dimensional Mean-Field Control with Non-local Interactions
topic Optimization and Control
url https://arxiv.org/abs/2405.10922