Multialternative Neural Decision Processes

2020/05/03 by Baldassi, Carlo, Cerreia-Vioglio, Simone, Maccheroni, Fabio +2
#Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Economics and business #Neurons and Cognition (q-bio.NC) #Theoretical Economics (econ.TH)

paper · doi:10.48550/arxiv.2005.01081

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.

Related

• Algorithmic Decision Processes
• Multinomial logit processes and preference discovery: inside and outside the black box
• Metacognition in multialternative choices is based on more information than type-1 decisions.
• A Supervised Goal Directed Algorithm in Economical Choice Behaviour: An Actor-Critic Approach
• Unveiling Options with Neural Decomposition