Paying to Do Better: Games with Payments between Learning Agents

2024-05-31

arXiv.org

AI Summary

This paper investigates how learning agents in repeated games—such as auctions—endogenously implement monetary transfers to strategically influence others’ behavior. Method: We propose the first formal model of cross-agent payment strategies, integrating game-theoretic modeling, online learning dynamics analysis, and equilibrium computation. Contribution/Results: We show that self-interested agents frequently adopt such payments—not only as a pervasive phenomenon but also one that often enhances social welfare. In both first-price and second-price auctions, these endogenous transfers can induce strong collusive equilibria that are low-revenue yet highly efficient, fundamentally altering strategy evolution trajectories and payoff allocations. Our work reveals a foundational challenge for mechanism design posed by endogenous inter-agent payments in autonomous systems, providing theoretical foundations for modeling novel strategic interactions and welfare regulation in digital ecosystems.

Technology Category

• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Mechanism Design
• Search and Optimization: Learning to Search

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

In repeated games, such as auctions, players typically use learning algorithms to choose their actions. The use of such autonomous learning agents has become widespread on online platforms. In this paper, we explore the impact of players incorporating monetary transfer policies into their agents' algorithms, aiming to influence behavior in their favor through the dynamics between the agents. Our focus is on understanding when players have incentives to make use of monetary transfers, how such payments may affect learning dynamics, and what the implications are for welfare and its distribution among the players. We propose a simple and general game-theoretic model to capture such scenarios. Our results on general games show that in a very broad class of games, self-interested players benefit from letting their learning agents make payments to other learners during the game dynamics, and that in many cases, this kind of behavior improves welfare for all players. Our results on first- and second-price auctions show that in equilibria of the ``payment policy game,'' the agents' dynamics reach strong collusive outcomes with low revenue for the auctioneer. These results raise new questions and highlight a challenge for mechanism design in systems where automated learning agents can benefit from interacting with their peers in the digital ecosystem and outside the boundaries of the mechanism.

Problem

• Impact of monetary transfers on learning agents
• Incentives for players to use payments
• Welfare implications of payment policies in games

Innovation

• Monetary transfer policies
• Game-theoretic model
• Automated learning agents