Well-posedness and propagation of chaos for multi-agent models with strategies and diffusive effects
Alessandro Baldi, Marco Morandotti

TL;DR
This paper introduces a multi-agent model with strategies and diffusive effects, proving well-posedness and demonstrating that as the number of agents increases, the system converges to a McKean--Vlasov equation, establishing a propagation of chaos.
Contribution
It provides the first rigorous proof of well-posedness and propagation of chaos for multi-agent systems with strategy-based states and diffusive dynamics.
Findings
Proved well-posedness of the multi-agent model.
Established convergence to McKean--Vlasov equation as agents increase.
Demonstrated propagation of chaos in the system.
Abstract
A multi-agent model for individuals endowed with strategies and subject to diffusive effects is proposed. The microscopic state of each agent is described by a spatial position and a probability measure, interpreted as a mixed strategy, over a compact metric space. The evolution is governed by a non-local interaction mechanism and by stochastic effects acting on the spatial component of the state. The well-posedness of the multi-agent system and that of a certain McKean--Vlasov stochastic differential equation are proved. Eventually, a propagation of chaos result is obtained, which guarantees that the former model converges to the latter as the number of agents goes to infinity.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
