Multi-Agent Inverse Reinforcement Learning for Identifying Pareto-Efficient Coordination -- A Distributionally Robust Approach

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Snow, Luke, Krishnamurthy, Vikram
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911149177438208
author Snow, Luke
Krishnamurthy, Vikram
author_facet Snow, Luke
Krishnamurthy, Vikram
contents Multi-agent inverse reinforcement learning (IRL) aims to identify Pareto-efficient behavior in a multi-agent system, and reconstruct utility functions of the individual agents. Motivated by the problem of detecting UAV coordination, how can we construct a statistical detector for Pareto-efficient behavior given noisy measurements of the decisions of a multi-agent system? This paper approaches this IRL problem by deriving necessary and sufficient conditions for a dataset of multi-agent system dynamics to be consistent with Pareto-efficient coordination, and providing algorithms for recovering utility functions which are consistent with the system dynamics. We derive an optimal statistical detector for determining Pareto-efficient coordination from noisy system measurements, which minimizes Type-I statistical detection error. Then, we provide a utility estimation algorithm which minimizes the worst-case estimation error over a statistical ambiguity set centered at empirical observations; this min-max solution achieves distributionally robust IRL, which is crucial in adversarial strategic interactions. We illustrate these results in a detailed example for detecting Pareto-efficient coordination among multiple UAVs given noisy measurement recorded at a radar. We then reconstruct the utility functions of the UAVs in a distributionally robust sense.
format Preprint
id arxiv_https___arxiv_org_abs_2509_08956
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Agent Inverse Reinforcement Learning for Identifying Pareto-Efficient Coordination -- A Distributionally Robust Approach
Snow, Luke
Krishnamurthy, Vikram
Systems and Control
Signal Processing
Multi-agent inverse reinforcement learning (IRL) aims to identify Pareto-efficient behavior in a multi-agent system, and reconstruct utility functions of the individual agents. Motivated by the problem of detecting UAV coordination, how can we construct a statistical detector for Pareto-efficient behavior given noisy measurements of the decisions of a multi-agent system? This paper approaches this IRL problem by deriving necessary and sufficient conditions for a dataset of multi-agent system dynamics to be consistent with Pareto-efficient coordination, and providing algorithms for recovering utility functions which are consistent with the system dynamics. We derive an optimal statistical detector for determining Pareto-efficient coordination from noisy system measurements, which minimizes Type-I statistical detection error. Then, we provide a utility estimation algorithm which minimizes the worst-case estimation error over a statistical ambiguity set centered at empirical observations; this min-max solution achieves distributionally robust IRL, which is crucial in adversarial strategic interactions. We illustrate these results in a detailed example for detecting Pareto-efficient coordination among multiple UAVs given noisy measurement recorded at a radar. We then reconstruct the utility functions of the UAVs in a distributionally robust sense.
title Multi-Agent Inverse Reinforcement Learning for Identifying Pareto-Efficient Coordination -- A Distributionally Robust Approach
topic Systems and Control
Signal Processing
url https://arxiv.org/abs/2509.08956