# Adaptive Decision Making via Entropy Minimization

arXiv: https://arxiv.org/abs/1803.06638 · HTML: https://mlsanity.com/paper/1803.06638/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2018.

## Built on by (most cited first, 2 of 2)

- [Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models](https://mlsanity.com/paper/2310.18127/) (2023)
- [Task-Aware Meta Learning-based Siamese Neural Network for Classifying Obfuscated Malware](https://mlsanity.com/paper/2110.13409/) (2021)

## Abstract (arXiv)

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-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.