Robust Reward Design for Markov Decision Processes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Shuo, Ma, Haoxiang, Fu, Jie, Han, Shuo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913381551702016
author Wu, Shuo
Ma, Haoxiang
Fu, Jie
Han, Shuo
author_facet Wu, Shuo
Ma, Haoxiang
Fu, Jie
Han, Shuo
contents The problem of reward design examines the interaction between a leader and a follower, where the leader aims to shape the follower's behavior to maximize the leader's payoff by modifying the follower's reward function. Current approaches to reward design rely on an accurate model of how the follower responds to reward modifications, which can be sensitive to modeling inaccuracies. To address this issue of sensitivity, we present a solution that offers robustness against uncertainties in modeling the follower, including 1) how the follower breaks ties in the presence of nonunique best responses, 2) inexact knowledge of how the follower perceives reward modifications, and 3) bounded rationality of the follower. Our robust solution is guaranteed to exist under mild conditions and can be obtained numerically by solving a mixed-integer linear program. Numerical experiments on multiple test cases demonstrate that our solution improves robustness compared to the standard approach without incurring significant additional computing costs.
format Preprint
id arxiv_https___arxiv_org_abs_2406_05086
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust Reward Design for Markov Decision Processes
Wu, Shuo
Ma, Haoxiang
Fu, Jie
Han, Shuo
Optimization and Control
Artificial Intelligence
Computer Science and Game Theory
The problem of reward design examines the interaction between a leader and a follower, where the leader aims to shape the follower's behavior to maximize the leader's payoff by modifying the follower's reward function. Current approaches to reward design rely on an accurate model of how the follower responds to reward modifications, which can be sensitive to modeling inaccuracies. To address this issue of sensitivity, we present a solution that offers robustness against uncertainties in modeling the follower, including 1) how the follower breaks ties in the presence of nonunique best responses, 2) inexact knowledge of how the follower perceives reward modifications, and 3) bounded rationality of the follower. Our robust solution is guaranteed to exist under mild conditions and can be obtained numerically by solving a mixed-integer linear program. Numerical experiments on multiple test cases demonstrate that our solution improves robustness compared to the standard approach without incurring significant additional computing costs.
title Robust Reward Design for Markov Decision Processes
topic Optimization and Control
Artificial Intelligence
Computer Science and Game Theory
url https://arxiv.org/abs/2406.05086