Inverse Reinforcement Learning with Sub-optimal Experts

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Poiani, Riccardo, Curti, Gabriele, Metelli, Alberto Maria, Restelli, Marcello
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916084128415744
author Poiani, Riccardo
Curti, Gabriele
Metelli, Alberto Maria
Restelli, Marcello
author_facet Poiani, Riccardo
Curti, Gabriele
Metelli, Alberto Maria
Restelli, Marcello
contents Inverse Reinforcement Learning (IRL) techniques deal with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act optimally in an underlying unknown task. In several problems of interest, however, it is possible to observe the behavior of multiple experts with different degree of optimality (e.g., racing drivers whose skills ranges from amateurs to professionals). For this reason, in this work, we extend the IRL formulation to problems where, in addition to demonstrations from the optimal agent, we can observe the behavior of multiple sub-optimal experts. Given this problem, we first study the theoretical properties of the class of reward functions that are compatible with a given set of experts, i.e., the feasible reward set. Our results show that the presence of multiple sub-optimal experts can significantly shrink the set of compatible rewards. Furthermore, we study the statistical complexity of estimating the feasible reward set with a generative model. To this end, we analyze a uniform sampling algorithm that results in being minimax optimal whenever the sub-optimal experts' performance level is sufficiently close to the one of the optimal agent.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03857
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Inverse Reinforcement Learning with Sub-optimal Experts
Poiani, Riccardo
Curti, Gabriele
Metelli, Alberto Maria
Restelli, Marcello
Machine Learning
Artificial Intelligence
Inverse Reinforcement Learning (IRL) techniques deal with the problem of deducing a reward function that explains the behavior of an expert agent who is assumed to act optimally in an underlying unknown task. In several problems of interest, however, it is possible to observe the behavior of multiple experts with different degree of optimality (e.g., racing drivers whose skills ranges from amateurs to professionals). For this reason, in this work, we extend the IRL formulation to problems where, in addition to demonstrations from the optimal agent, we can observe the behavior of multiple sub-optimal experts. Given this problem, we first study the theoretical properties of the class of reward functions that are compatible with a given set of experts, i.e., the feasible reward set. Our results show that the presence of multiple sub-optimal experts can significantly shrink the set of compatible rewards. Furthermore, we study the statistical complexity of estimating the feasible reward set with a generative model. To this end, we analyze a uniform sampling algorithm that results in being minimax optimal whenever the sub-optimal experts' performance level is sufficiently close to the one of the optimal agent.
title Inverse Reinforcement Learning with Sub-optimal Experts
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2401.03857