Learning in Online Principal-Agent Interactions: The Power of Menus

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Han, Minbiao, Albert, Michael, Xu, Haifeng
Format: Preprint
Veröffentlicht: 2023
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913180965404672
author Han, Minbiao
Albert, Michael
Xu, Haifeng
author_facet Han, Minbiao
Albert, Michael
Xu, Haifeng
contents We study a ubiquitous learning challenge in online principal-agent problems during which the principal learns the agent's private information from the agent's revealed preferences in historical interactions. This paradigm includes important special cases such as pricing and contract design, which have been widely studied in recent literature. However, existing work considers the case where the principal can only choose a single strategy at every round to interact with the agent and then observe the agent's revealed preference through their actions. In this paper, we extend this line of study to allow the principal to offer a menu of strategies to the agent and learn additionally from observing the agent's selection from the menu. We provide a thorough investigation of several online principal-agent problem settings and characterize their sample complexities, accompanied by the corresponding algorithms we have developed. We instantiate this paradigm to several important design problems $-$ including Stackelberg (security) games, contract design, and information design. Finally, we also explore the connection between our findings and existing results about online learning in Stackelberg games, and we offer a solution that can overcome a key hard instance of Peng et al. (2019).
format Preprint
id arxiv_https___arxiv_org_abs_2312_09869
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Learning in Online Principal-Agent Interactions: The Power of Menus
Han, Minbiao
Albert, Michael
Xu, Haifeng
Computer Science and Game Theory
Machine Learning
We study a ubiquitous learning challenge in online principal-agent problems during which the principal learns the agent's private information from the agent's revealed preferences in historical interactions. This paradigm includes important special cases such as pricing and contract design, which have been widely studied in recent literature. However, existing work considers the case where the principal can only choose a single strategy at every round to interact with the agent and then observe the agent's revealed preference through their actions. In this paper, we extend this line of study to allow the principal to offer a menu of strategies to the agent and learn additionally from observing the agent's selection from the menu. We provide a thorough investigation of several online principal-agent problem settings and characterize their sample complexities, accompanied by the corresponding algorithms we have developed. We instantiate this paradigm to several important design problems $-$ including Stackelberg (security) games, contract design, and information design. Finally, we also explore the connection between our findings and existing results about online learning in Stackelberg games, and we offer a solution that can overcome a key hard instance of Peng et al. (2019).
title Learning in Online Principal-Agent Interactions: The Power of Menus
topic Computer Science and Game Theory
Machine Learning
url https://arxiv.org/abs/2312.09869