Modelling virtual bargaining using logical representation change

Alan Bundy, Eugene Philalithis, Xue Li

Research output: Chapter in Book/Report/Conference proceedingChapter (peer-reviewed)peer-review


We discuss work in progress on the computational modelling of virtual bargaining: inference-driven human coordination under severe communicative constraints. For this initial work we model variants of a two-player coordination game of item selection and avoidance taken from the current virtual bargaining literature. In this range of games, human participants collaborate to select items (e.g. bananas) or avoid items (e.g. scorpions), based on signalling conventions constructed and updated from shared assumptions, with minimal information exchange. We model behaviours in these games using logic programs interpretable as logical theories. From an initial theory comprised of rules, background assumptions and a basic signalling convention, we use automated theory repair to jointly adapt that basic signalling convention to novel contexts, with no explicit coordination between players. Our ABC system for theory repair delivers spontaneous adaptation, using reasoning failures to replace established conventions with better alternatives, matching human players’ own reasoning across several games.
Original languageEnglish
Title of host publicationHuman-Like Machine Intelligence
EditorsStephen H. Muggleton, Nicholas Chater
PublisherOxford University Press
ISBN (Print)9780198862536
Publication statusPublished - 20 Jul 2021


  • virtual bargaining
  • joint action
  • human-like intelligence
  • automated theory repair
  • automated reasoning
  • belief revision
  • reformation
  • Datalog


Dive into the research topics of 'Modelling virtual bargaining using logical representation change'. Together they form a unique fingerprint.

Cite this