Theory of Mind as Intrinsic Motivation for Multi-Agent Reinforcement Learning

Autor:	Oguntola, Ini, Campbell, Joseph, Stepputtis, Simon, Sycara, Katia
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Multiagent Systems
Druh dokumentu:	Working Paper
Popis:	The ability to model the mental states of others is crucial to human social intelligence, and can offer similar benefits to artificial agents with respect to the social dynamics induced in multi-agent settings. We present a method of grounding semantically meaningful, human-interpretable beliefs within policies modeled by deep networks. We then consider the task of 2nd-order belief prediction. We propose that ability of each agent to predict the beliefs of the other agents can be used as an intrinsic reward signal for multi-agent reinforcement learning. Finally, we present preliminary empirical results in a mixed cooperative-competitive environment. Comment: To appear at ICML 2023 Workshop on Theory of Mind
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2307.01158 Zobrazit plný text záznamu View this record from Arxiv