Learning A Game By Paying The Agents

Abstract

We study the problem of learning the utility functions of no-regret learning agents in a repeated normal-form game. Differing from most prior literature, we introduce a principal with the power to observe the agents playing the game, send agents signals, and give agents payments as a function of their actions. We show that the principal can, using a number of rounds polynomial in the size of the game, learn the utility functions of all agents to any desired precision \(\epsilon > 0\), for any no-regret learning algorithms of the agents. Our main technique is to formulate a zero-sum game between the principal and the agents, where the principal chooses strategies among the set of all payment functions to minimize the agent's payoff. Finally, we discuss implications for the problem of steering agents. We introduce, using our utility-learning algorithm as a subroutine, the first algorithm for steering arbitrary no-regret learning agents to a desired equilibrium without prior knowledge of

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2025learning

Related papers

• Mechanisms For A No-regret Agent: Beyond The Common Prior (2020)0.00
• Stochastic Principal-agent Problems: Efficient Computation And Learning (2023)0.00
• Impact Of Decentralized Learning On Player Utilities In Stackelberg Games (2024)0.00
• Principal-agent Bandit Games With Self-interested And Exploratory Learning Agents (2024)0.00
• Maximizing Utility In Multi-agent Environments By Anticipating The Behavior Of Other Learners (2024)2.26
• Algorithmic Pricing With Independent Learners And Relative Experience Replay (2021)0.00
• What Game Are We Playing? End-to-end Learning In Normal And Extensive Form Games (2018)0.00
• Opponent Learning Awareness And Modelling In Multi-objective Normal Form Games (2020)7.16