An active learning method for solving competitive multi-agent decision-making and control problems

arXiv:2212.12561v3 Announce Type: replace-cross
Abstract: To identify a stationary action profile for a population of competitive agents, each executing private strategies, we introduce a novel active-learning scheme where a centralized external observer (or entity) can probe the agents' reactions and recursively update simple local parametric estimates of the action-reaction mappings. Under very general working assumptions (not even assuming that a stationary profile exists), sufficient conditions are established to assess the asymptotic properties of the proposed active learning methodology so that, …

abstract active learning agent agents arxiv control cs.lg cs.ma cs.sy decision eess.sy identify making math.oc multi-agent novel parametric population probe profile simple strategies type update