English

Adaptive Decision Making via Entropy Minimization

Data Analysis, Statistics and Probability 2018-12-04 v2 Statistical Mechanics Computer Science and Game Theory

Abstract

An agent choosing between various actions tends to take the one with the lowest cost. But this choice is arguably too rigid (not adaptive) to be useful in complex situations, e.g., where exploration-exploitation trade-off is relevant in creative task solving or when stated preferences differ from revealed ones. Here we study an agent who is willing to sacrifice a fixed amount of expected utility for adaptation. How can/ought our agent choose an optimal (in a technical sense) mixed action? We explore consequences of making this choice via entropy minimization, which is argued to be a specific example of risk-aversion. This recovers the ϵ\epsilon-greedy probabilities known in reinforcement learning. We show that the entropy minimization leads to rudimentary forms of intelligent behavior: (i) the agent assigns a non-negligible probability to costly events; but (ii) chooses with a sizable probability the action related to less cost (lesser of two evils) when confronted with two actions with comparable costs; (iii) the agent is subject to effects similar to cognitive dissonance and frustration. Neither of these features are shown by entropy maximization.

Keywords

Cite

@article{arxiv.1803.06638,
  title  = {Adaptive Decision Making via Entropy Minimization},
  author = {Armen E. Allahverdyan and Aram Galstyan and Ali E. Abbas and Zbigniew R. Struzik},
  journal= {arXiv preprint arXiv:1803.06638},
  year   = {2018}
}

Comments

21 pages, 3 figures

R2 v1 2026-06-23T00:56:39.181Z