Information, Utility & Bounded Rationality

TL;DR

This paper introduces a thermodynamic-inspired axiomatic framework for bounded rational decision-making, balancing utility maximization with information costs, leading to stochastic policies and naturally deriving risk-sensitive and robust control schemes.

Contribution

It formulates a variational 'free utility' principle for bounded rationality, unifying stochastic control, risk sensitivity, and robustness within a thermodynamic interpretation.

Findings

Bounded optimal control solutions are derived from the free utility principle.

Risk-sensitive and robust control schemes emerge naturally from the framework.

Ignoring resource costs recovers the maximum expected utility principle.

Abstract

Perfectly rational decision-makers maximize expected utility, but crucially ignore the resource costs incurred when determining optimal actions. Here we employ an axiomatic framework for bounded rational decision-making based on a thermodynamic interpretation of resource costs as information costs. This leads to a variational "free utility" principle akin to thermodynamical free energy that trades off utility and information costs. We show that bounded optimal control solutions can be derived from this variational principle, which leads in general to stochastic policies. Furthermore, we show that risk-sensitive and robust (minimax) control schemes fall out naturally from this framework if the environment is considered as a bounded rational and perfectly rational opponent, respectively. When resource costs are ignored, the maximum expected utility principle is recovered.