On Multi-Agent Inverse Reinforcement Learning

Autor:	Freihaut, Till, Ramponi, Giorgia
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	In multi-agent systems, the agent behavior is highly influenced by its utility function, as these utilities shape both individual goals as well as interactions with the other agents. Inverse Reinforcement Learning (IRL) is a well-established approach to inferring the utility function by observing an expert behavior within a given environment. In this paper, we extend the IRL framework to the multi-agent setting, assuming to observe agents who are following Nash Equilibrium (NE) policies. We theoretically investigate the set of utilities that explain the behavior of NE experts. Specifically, we provide an explicit characterization of the feasible reward set and analyze how errors in estimating the transition dynamics and expert behavior impact the recovered rewards. Building on these findings, we provide the first sample complexity analysis for the multi-agent IRL problem. Finally, we provide a numerical evaluation of our theoretical results. Comment: Currently under review
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2411.15046 Zobrazit plný text záznamu View this record from Arxiv