Multialternative Neural Decision Processes
arXiv:2005.01081v51 citations
Originality Synthesis-oriented
AI Analysis
This addresses decision-making processes in AI, but appears incremental as it builds on existing concepts like binary comparisons and Markovian exploration.
The paper tackles the problem of multialternative choice by introducing an algorithmic decision process that combines binary comparisons and Markovian exploration, and shows that transitivity makes it testable.
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.