Boltzmann social learning with heterogeneous rationality
Abstract
This paper analyzes a novel social learning model in which, at each discrete time step, agents with private preferences repeatedly select actions via a softmax (Boltzmann) rule, and update their preferences based on public observations of others’ choices. This work addresses a critical gap by introducing rational heterogeneity through agent-specific rationality parameters . Unlike previous models, our approach accounts for the diverse ways individuals process social information by using a discrete-time deterministic mean-field approximation map. We establish fundamental equilibrium properties that were previously unexplored. In particular, we prove the existence of fixed points and show that, on complete graphs, every mean-field equilibrium is a consensus state, where all agents share identical preferences. We further derive sufficient conditions for the uniqueness of this equilibrium and its local asymptotic stability. Numerical simulations validate our theoretical findings and illustrate how rational heterogeneity and network structure interact to shape collective behavior in social learning systems.
Related
- Learning Nonlocal Interactions in Large-Scale Heterogeneous Metamaterials through Scientific Machine Learning
- Quantum Federated Learning Based on Bures--Uhlmann Geometry for Heterogeneous Noisy Clients
- Thermodynamically Consistent Machine Learning for Fracture Prediction in Heterogeneous Materials
- Learning shared hyperelastic constitutive representation from heterogeneous full-field experiments across multiple materials
- Q-RAIL: A Reliability-Aware Framework for Quantum Federated Learning on Heterogeneous Noisy Hardware
BibTeX
@article{chaddad2026boltzmann,
title = {{Boltzmann social learning with heterogeneous rationality}},
author = {Sylvie Chaddad and Yezekael Hayel and Vineeth Varma and Nicolas Gast},
journal = {Nonlinear Analysis: Hybrid Systems},
year = {2026},
month = oct,
doi = {10.1016/j.nahs.2026.101718},
url = {https://hal.science/hal-05583966v1},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Boltzmann social learning with heterogeneous rationality
AU - Sylvie Chaddad
AU - Yezekael Hayel
AU - Vineeth Varma
AU - Nicolas Gast
PY - 2026
DA - 2026/10/29
JO - Nonlinear Analysis: Hybrid Systems
DO - 10.1016/j.nahs.2026.101718
UR - https://hal.science/hal-05583966v1
AB - This paper analyzes a novel social learning model in which, at each discrete time step, agents with private preferences repeatedly select actions via a softmax (Boltzmann) rule, and update their preferences based on public observations of others’ choices. This work addresses a critical gap by introducing rational heterogeneity through agent-specific rationality parameters . Unlike previous models, our approach accounts for the diverse ways individuals process social information by using a discrete-time deterministic mean-field approximation map. We establish fundamental equilibrium properties that were previously unexplored. In particular, we prove the existence of fixed points and show that, on complete graphs, every mean-field equilibrium is a consensus state, where all agents share identical preferences. We further derive sufficient conditions for the uniqueness of this equilibrium and its local asymptotic stability. Numerical simulations validate our theoretical findings and illustrate how rational heterogeneity and network structure interact to shape collective behavior in social learning systems.
SN - 1751-570X
ER -