Systems of bounded rational agents with information-theoretic constraints
Braun, Daniel A.
FacultiesFakultät für Ingenieurwissenschaften, Informatik und Psychologie
InstitutionsInstitut für Neuroinformatik
Neural Computation ; 31 (2019), 2. - S. 440-476. - ISSN 0899-7667. - eISSN 1530-888X
Link to original publicationhttps://dx.doi.org/10.1162/neco_a_01153
LicenseCC BY 4.0 International
Specialization and hierarchical organization are important features of efficient collaboration in economical, artificial, and biological systems. Here, we investigate the hypothesis that both features can be explained by the fact that each entity of such a system is limited in a certain way. We propose an information-theoretic approach based on a free energy principle in order to computationally analyze systems of bounded ra- tional agents that deal with such limitations optimally. We find that specialization allows a focus on fewer tasks, thus leading to a more effi- cient execution, but in turn, it requires coordination in hierarchical struc- tures of specialized experts and coordinating units. Our results suggest that hierarchical architectures of specialized units at lower levels that are coordinated by units at higher levels are optimal, given that each unit’s information-processing capability is limited and conforms to constraints on complexity costs.
BRISC / Bounded Rationality in Sensorimotor Coordination / EC / H2020 / 678082
Subject HeadingsEingeschränkte Rationalität [GND]
Multiagent systems [LCSH]