Similar failures of consideration arise in human and machine planning.

Journal: Cognition
PMID:

Abstract

Humans are remarkably efficient at decision making, even in "open-ended" problems where the set of possible actions is too large for exhaustive evaluation. Our success relies, in part, on processes for calling to mind the right candidate actions. When these processes fail, the result is a kind of puzzle in which the value of a solution would be obvious once it is considered, but never gets considered in the first place. Recently, machine learning (ML) architectures have attained or even exceeded human performance on open-ended decision making tasks such as playing chess and Go. We ask whether the broad architectural principles that underlie ML success in these domains generate similar consideration failures to those observed in humans. We demonstrate a case in which they do, illuminating how humans make open-ended decisions, how this relates to ML approaches to similar problems, and how both architectures lead to characteristic patterns of success and failure.

Authors

  • Alice Zhang
    Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139, United States of America; Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, United States of America. Electronic address: alice.zhang@psy.ox.ac.uk.
  • Max Langenkamp
    Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA 02139, United States of America. Electronic address: maxlangenkamp@me.com.
  • Max Kleiman-Weiner
    Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology, Cambridge, MA 02139, United States of America. Electronic address: maxkw@uw.edu.
  • Tuomas Oikarinen
    McGovern Institute for Brain Research, Massachusetts Institute of Technology, 43 Vassar Street, Cambridge, Massachusetts 02139, USA.
  • Fiery Cushman
    Department of Psychology, Harvard University, Cambridge, USA. cushman@fas.harvard.edu.