Occupation-Measure Mean-Field Control: Optimization over Measures and Frank-Wolfe Methods

TL;DR

This paper presents a novel convex optimization framework for large-population control using occupation measures, solved efficiently with Frank-Wolfe algorithms, demonstrated through UAV and satellite control experiments.

Contribution

It introduces occupation-measure mean-field control, a new convex measure-based approach with Frank-Wolfe algorithms for scalable large-population control.

Findings

Framework is convex under certain conditions.

Algorithms converge with theoretical guarantees.

Effective in high-dimensional, constrained environments.

Abstract

Coordinating large populations of autonomous agents, such as UAV swarms or satellite constellations, poses significant computational challenges for traditional multi-agent control methods. This paper introduces a new optimization framework for large-population control, termed occupation-measure mean-field control (OM-MFC). The framework models the evolution of agent populations directly in the space of occupation measures and casts large-population control as an infinite-dimensional optimization problem over measures, which becomes convex under a positive-semidefiniteness condition on the interaction kernel. A Frank--Wolfe (FW) algorithm and its fully-corrective variant (FCFW) are developed to solve the resulting problem efficiently, where each iteration reduces to a classical optimal control subproblem. Theoretical results establish convexity, existence of optimal solutions, and convergence guarantees of the proposed algorithms. Owing to its measure-based formulation, the framework naturally accommodates systems with very large numbers of agents. Numerical experiments on UAV swarm coordination and satellite constellation control demonstrate the scalability and effectiveness of the proposed approach in high-dimensional and constrained environments.