Thermodynamics as a theory of decision-making with information processing costs

TL;DR

This paper introduces a thermodynamic framework for decision-making that incorporates information processing costs, modeling bounded rationality as a trade-off between utility and computational effort, grounded in statistical physics.

Contribution

It provides an axiomatic derivation of bounded rational decision-making using thermodynamic free energy, linking decision theory with statistical physics concepts.

Findings

Bounded rationality modeled as thermodynamic machines.

Decision-making balances utility and information costs.

Framework recovers expected utility maximization when costs are ignored.

Abstract

Perfectly rational decision-makers maximize expected utility, but crucially ignore the resource costs incurred when determining optimal actions. Here we propose an information-theoretic formalization of bounded rational decision-making where decision-makers trade off expected utility and information processing costs. Such bounded rational decision-makers can be thought of as thermodynamic machines that undergo physical state changes when they compute. Their behavior is governed by a free energy functional that trades off changes in internal energy-as a proxy for utility-and entropic changes representing computational costs induced by changing states. As a result, the bounded rational decision-making problem can be rephrased in terms of well-known concepts from statistical physics. In the limit when computational costs are ignored, the maximum expected utility principle is recovered. We discuss the relation to satisficing decision-making procedures as well as links to existing theoretical frameworks and human decision-making experiments that describe deviations from expected utility theory. Since most of the mathematical machinery can be borrowed from statistical physics, the main contribution is to axiomatically derive and interpret the thermodynamic free energy as a model of bounded rational decision-making.