A Foundational Approach to Generalising the Maximum Entropy Inference Process to the Multi-Agent Context

Autor: George Wilmers
Jazyk: angličtina
Rok vydání: 2015
Předmět:
Zdroj: Entropy, Vol 17, Iss 2, Pp 594-645 (2015)
Druh dokumentu: article
ISSN: 1099-4300
DOI: 10.3390/e17020594
Popis: The present paper seeks to establish a logical foundation for studying axiomatically multi-agent probabilistic reasoning over a discrete space of outcomes. We study the notion of a social inference process which generalises the concept of an inference process for a single agent which was used by Paris and Vencovská to characterise axiomatically the method of maximum entropy inference. Axioms for a social inference process are introduced and discussed, and a particular social inference process called the Social Entropy Process, or SEP, is defined which satisfies these axioms. SEP is justified heuristically by an information theoretic argument, and incorporates both the maximum entropy inference process for a single agent and the multi–agent normalised geometric mean pooling operator.
Databáze: Directory of Open Access Journals