Multialternative Neural Decision Processes

TL;DR

This paper presents a new algorithmic decision process for multialternative choices that integrates binary comparisons with Markovian exploration, and demonstrates how transitivity as a property makes the model testable.

Contribution

The paper introduces a novel multialternative decision process combining binary comparisons and Markovian exploration, with a focus on transitivity for testability.

Findings

Transitivity property makes the decision process testable.

The model effectively combines binary comparisons with exploration.

The approach advances understanding of multialternative decision mechanisms.

Abstract

We introduce an algorithmic decision process for multialternative choice that combines binary comparisons and Markovian exploration. We show that a preferential property, transitivity, makes it testable.