2025/07/31 by Sun, Renyan, Ashutosh Nayyar, Nayyar, Ashutosh
Computer Science · Decision Sciences · #Computer Science and Game Theory (cs.GT) #Distributed Control Multi-Agent Systems #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Mathematics #Game Theory and Applications #Optimization and Control (math.OC) #Reinforcement Learning in Robotics #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2508.00188
openalex publication_date 2025/07/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We consider a finite-horizon discrete-time dynamic system jointly controlled by a designer and one or more agents, where the designer can influence the agents' actions through selective information disclosure. At each time step, the designer sends a message to the agent(s) from a prespecified message space. The designer may also take an action that directly influences system dynamics and rewards. Each agent uses its received message (and its own information) to choose its action. We are interested in the setting where the designer would like to incentivize each agent to play a specific strategy. We consider a notion of incentive compatibility that is based on sequential rationality at each realization of the common information between the designer and the agent(s). Our objective is to find a messaging and action strategy for the designer that maximizes its total expected reward while incentivizing each agent to follow a prespecified strategy. Under certain assumptions on the information structure of the problem, we show that an optimal designer strategy can be computed using a backward inductive algorithm that solves a family of linear programs.