Thermodynamics as a theory of decision-making with information-processing costs
From MaRDI portal
Publication:5362138
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.
Recommendations
- Information-theoretic bounded rationality and -optimality
- A reward-maximizing spiking neuron as a bounded rational decision maker
- Information theory and observational limitations in decision making
- An information theoretic model of bounded rationality
- Connecting Brillouin's principle to a social synergetics probabilistic model. Applications to the binary decision problems
Cited in
(21)- Connecting Brillouin's principle to a social synergetics probabilistic model. Applications to the binary decision problems
- Adaptive decision making via entropy minimization
- Energy-information coupling during integrative cognitive processes
- Representing preorders with injective monotones
- Bounded rationality in learning, perception, decision-making, and stochastic games
- Asymmetric micro-dynamics in spatial anonymous public goods game
- Information-theoretic bounded rationality and -optimality
- Bio-inspired feedback-circuit implementation of discrete, free energy optimizing, winner-take-all computations
- Systems of Bounded Rational Agents with Information-Theoretic Constraints
- A free energy principle for biological systems
- Free utility model for explaining the social gravity law
- A minimum free energy model of motor learning
- A reward-maximizing spiking neuron as a bounded rational decision maker
- Active inference: a process theory
- Active inference, curiosity and insight
- The Boltzmann distribution in the problem of rational choice by population of a patch under an imperfect information about its resources
- Simultaneous perception-action design via invariant finite belief sets
- Bounded rationality for relaxing best response and mutual consistency: the quantal hierarchy model of decision making
- Bayes, bounds, and rational analysis
- A universal modeling framework for travel choice behavior
- A free energy and maximum entropy model of the Shafir-Tversky prisoner's dilemma experiment
This page was built for publication: Thermodynamics as a theory of decision-making with information-processing costs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5362138)
