Outcome matrix based phrase selection

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

Abstract

This article presents a method for using outcome matrices for social phrase selection. An outcome matrix is a computational representation of interaction often used to represent a social decision problem. Typically an outcome matrix lists the potential actions that a robot or agent might select and how the selection of each possible action will impact both the agent and their interactive partner. Here we examine the possibility of replacing the social actions listed in a matrix with phrases that could be spoken by the robot. We show that doing so allows one to utilize several tools from interdependence theory and game theory.

Original languageEnglish (US)
Title of host publicationBuilding Representations of Common Ground with Intelligent Agents - Papers from the AAAI Fall Symposium, Technical Report
Pages41-46
Number of pages6
StatePublished - Dec 1 2011
Event2011 AAAI Fall Symposium - Arlington, VA, United States
Duration: Nov 4 2011Nov 6 2011

Publication series

NameAAAI Fall Symposium - Technical Report
VolumeFS-11-02

Other

Other2011 AAAI Fall Symposium
CountryUnited States
CityArlington, VA
Period11/4/1111/6/11

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint Dive into the research topics of 'Outcome matrix based phrase selection'. Together they form a unique fingerprint.

  • Cite this

    Wagner, A. R. (2011). Outcome matrix based phrase selection. In Building Representations of Common Ground with Intelligent Agents - Papers from the AAAI Fall Symposium, Technical Report (pp. 41-46). (AAAI Fall Symposium - Technical Report; Vol. FS-11-02).