Reinforcement Learning, not Supervised Learning, Can Lead to Insight

Arata Nonami, Haruaki Fukuda, Yoshiyuki Sato, Kazuyuki Samejima, Kazuhiro Ueda

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This study examined the differences among individuals in the performance of insight problem solving. The problem-solving characteristics of an individual seemed to be dependent on what and how they had learned. Thus, we compared the performances of insight problem solving between reinforcement and supervised learners. The results showed that the performances of reinforcement learners were better than those of supervised learners, although the non-insight problem solving performance of both learner types was comparable. This result suggests that insight might be supported by the cognitive mechanisms underlying reinforcement learning. In particular, we speculate that the degree of exploration, by which reinforcement learning is characterized, might have an impact on the performance of insight problem solving.

Original languageEnglish
Title of host publicationProceedings of the 40th Annual Meeting of the Cognitive Science Society, CogSci 2018
PublisherThe Cognitive Science Society
Pages2161-2166
Number of pages6
ISBN (Electronic)9780991196784
Publication statusPublished - 2018
Externally publishedYes
Event40th Annual Meeting of the Cognitive Science Society: Changing Minds, CogSci 2018 - Madison, United States
Duration: 2018 Jul 252018 Jul 28

Publication series

NameProceedings of the 40th Annual Meeting of the Cognitive Science Society, CogSci 2018

Conference

Conference40th Annual Meeting of the Cognitive Science Society: Changing Minds, CogSci 2018
Country/TerritoryUnited States
CityMadison
Period18/7/2518/7/28

Keywords

  • exploration
  • insight problem solving
  • reinforcement learning
  • supervised learning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Human-Computer Interaction
  • Cognitive Neuroscience

Fingerprint

Dive into the research topics of 'Reinforcement Learning, not Supervised Learning, Can Lead to Insight'. Together they form a unique fingerprint.

Cite this