Learning human search strategies from a crowdsourcing game

Thurston Sexton, Max Yi Ren

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

Abstract

There is evidence that humans can be more efficient than existing algorithms at searching for good solutions in highdimensional and non-convex design or control spaces, potentially due to our prior knowledge and learning capability. This work attempts to quantify the search strategy of human beings to enhance a Bayesian optimization (BO) algorithm for an optimal design and control problem. We consider the sequence of human solutions as generated from BO, and propose to recover the algorithmic parameters of BO by maximizing the likelihood of the observed solution path. The method is different from inverse reinforcement learning (where an optimal control solution is learned based on human demonstrations) in that the latter requires near-optimal solutions from humans, while we only require the existence of a good search strategy. The method is first verified through simulation studies and then applied to the human solutions crowdsourced through a gamification of the problem under study [1]. We learn BO parameters from a player with a demonstrated good search strategy and show that applying the BO algorithm with these parameters to the game noticeably improves the convergence of the search from using a default BO setting.

Original languageEnglish (US)
Title of host publication42nd Design Automation Conference
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791850107
DOIs
StatePublished - 2016
EventASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2016 - Charlotte, United States
Duration: Aug 21 2016Aug 24 2016

Publication series

NameProceedings of the ASME Design Engineering Technical Conference
Volume2A-2016

Other

OtherASME 2016 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2016
Country/TerritoryUnited States
CityCharlotte
Period8/21/168/24/16

ASJC Scopus subject areas

  • Mechanical Engineering
  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Modeling and Simulation

Fingerprint

Dive into the research topics of 'Learning human search strategies from a crowdsourcing game'. Together they form a unique fingerprint.

Cite this