Effectively Learning from Pedagogical Demonstrations

Mark K. Ho, Michael L. Littman, Fiery Cushman, Joseph L. Austerweil

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

14 Scopus citations

Abstract

When observing others' behavior, people use Theory of Mind to infer unobservable beliefs, desires, and intentions. And when showing what activity one is doing, people will modify their behavior in order to facilitate more accurate interpretation and learning by an observer. Here, we present a novel model of how demonstrators act and observers interpret demonstrations corresponding to different levels of recursive social reasoning (i.e. a cognitive hierarchy) grounded in Theory of Mind. Our model can explain how demonstrators show others how to perform a task and makes predictions about how sophisticated observers can reason about communicative intentions. Additionally, we report an experiment that tests (1) how well an observer can learn from demonstrations that were produced with the intent to communicate, and (2) how an observer's interpretation of demonstrations influences their judgments.

Original languageEnglish
Title of host publicationProceedings of the 40th Annual Meeting of the Cognitive Science Society, CogSci 2018
Pages505-510
Number of pages6
ISBN (Electronic)9780991196784
StatePublished - 2018
Event40th Annual Meeting of the Cognitive Science Society: Changing Minds, CogSci 2018 - Madison, United States
Duration: 25 Jul 201828 Jul 2018

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
Period25/07/1828/07/18

Keywords

  • Bayesian Pedagogy
  • Cognitive Hierarchy
  • Communicative Intent
  • Reinforcement Learning
  • Theory of Mind

Fingerprint

Dive into the research topics of 'Effectively Learning from Pedagogical Demonstrations'. Together they form a unique fingerprint.

Cite this