2024/05/31 by Yoav Kolumbus, Kolumbus, Yoav, Joe Halpern +3
Computer Science · Decision Sciences · #91A05 #91A06 #91A10 #91A20 #91A40 #91A80 #Artificial Intelligence (cs.AI) #Auction Theory and Applications #Computer Science and Game Theory (cs.GT) #F.0 #FOS: Computer and information sciences #FOS: Economics and business #I.2 #I.2.6 #J.4 #Multi-Agent Systems and Negotiation #Multiagent Systems (cs.MA) #Theoretical Economics (econ.TH)
paper · pdf · doi:10.48550/arxiv.2405.20880
openalex publication_date 2024/05/31 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/30
In repeated games, such as auctions, players rely on autonomous learning agents to choose their actions. We study settings in which players have their agents make monetary transfers to other agents during play at their own expense, in order to influence learning dynamics in their favor. Our goal is to understand when players have incentives to use such payments, how payments between agents affect learning outcomes, and what the resulting implications are for welfare and its distribution. We propose a simple game-theoretic model to capture the incentive structure of such scenarios. We find that, quite generally, abstaining from payments is not robust to strategic deviations by users of learning agents: self-interested players benefit from having their agents make payments to other learners. In a broad class of games, such endogenous payments between learning agents lead to higher welfare for all players. In first- and second-price auctions, equilibria of the induced "payment-policy game" lead to highly collusive learning outcomes, with low or vanishing revenue for the auctioneer. These results highlight a fundamental challenge for mechanism design, as well as for regulatory policies, in environments where learning agents may interact in the digital ecosystem beyond a mechanism's boundaries.