Learning a Game by Paying the Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918495057346560 |
|---|---|
| author | Zhang, Brian Hu Lin, Tao Chen, Yiling Sandholm, Tuomas |
| author_facet | Zhang, Brian Hu Lin, Tao Chen, Yiling Sandholm, Tuomas |
| contents | 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 $ε> 0$, 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 their utility functions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01976 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning a Game by Paying the Agents Zhang, Brian Hu Lin, Tao Chen, Yiling Sandholm, Tuomas Computer Science and Game Theory 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 $ε> 0$, 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 their utility functions. |
| title | Learning a Game by Paying the Agents |
| topic | Computer Science and Game Theory |
| url | https://arxiv.org/abs/2503.01976 |