Systems of bounded rational agents with information-theoretic constraints
This addresses the problem of designing efficient collaborative systems in economics, AI, and biology, though it appears incremental as it builds on existing information-theoretic frameworks.
The paper tackles the problem of how specialization and hierarchical organization emerge in collaborative systems by proposing an information-theoretic approach based on a Free Energy principle to analyze bounded rational agents with limited information-processing capabilities. The results show that hierarchical architectures with specialized lower-level units coordinated by higher-level units are optimal under these constraints.
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 rational agents that deal with such limitations optimally. We find that specialization allows to focus on fewer tasks, thus leading to a more efficient execution, but in turn requires coordination in hierarchical structures 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.