English

Boltzmann State-Dependent Rationality

Artificial Intelligence 2024-04-30 v1 Robotics

Abstract

This paper expands on existing learned models of human behavior via a measured step in structured irrationality. Specifically, by replacing the suboptimality constant β\beta in a Boltzmann rationality model with a function over states β(s)\beta(s), we gain natural expressivity in a computationally tractable manner. This paper discusses relevant mathematical theory, sets up several experimental designs, presents limited preliminary results, and proposes future investigations.

Keywords

Cite

@article{arxiv.2404.17725,
  title  = {Boltzmann State-Dependent Rationality},
  author = {Osher Lerner},
  journal= {arXiv preprint arXiv:2404.17725},
  year   = {2024}
}
R2 v1 2026-06-28T16:08:14.182Z