@inproceedings{71cfe0e4efa24e978d7bd9ee96f3c6b4,
title = "Principal-Agent Reward Shaping in MDPs",
abstract = "Principal-agent problems arise when one party acts on behalf of another, leading to conflicts of interest. The economic literature has extensively studied principal-agent problems, and recent work has extended this to more complex scenarios such as Markov Decision Processes (MDPs). In this paper, we further explore this line of research by investigating how reward shaping under budget constraints can improve the principal's utility. We study a two-player Stackelberg game where the principal and the agent have different reward functions, and the agent chooses an MDP policy for both players. The principal offers an additional reward to the agent, and the agent picks their policy selfishly to maximize their reward, which is the sum of the original and the offered reward. Our results establish the NP-hardness of the problem and offer polynomial approximation algorithms for two classes of instances: Stochastic trees and deterministic decision processes with a finite horizon.",
author = "Omer Ben-Porat and Yishay Mansour and Michal Moshkovitz and Boaz Taitler",
note = "Publisher Copyright: Copyright {\textcopyright} 2024, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.; 38th AAAI Conference on Artificial Intelligence, AAAI 2024 ; Conference date: 20-02-2024 Through 27-02-2024",
year = "2024",
month = mar,
day = "25",
doi = "https://doi.org/10.1609/aaai.v38i9.28805",
language = "الإنجليزيّة",
series = "Proceedings of the AAAI Conference on Artificial Intelligence",
number = "9",
pages = "9502--9510",
editor = "Michael Wooldridge and Jennifer Dy and Sriraam Natarajan",
booktitle = "Technical Tracks 14",
edition = "9",
}