Learning Actions Models: Qualitative Approach

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

395 Downloads (Pure)


In dynamic epistemic logic, actions are described using action models. In this paper we introduce a framework for studying learnability of action models from observations. We present first results concerning propositional action models. First we check two basic learnability criteria: finite identifiability (conclusively inferring the appropriate action model in finite time) and identifiability in the limit (inconclusive convergence to the right action model). We show that deterministic actions are finitely identifiable, while non-deterministic actions require more learning power—they are identifiable in the limit.We then move on to a particular learning method, which proceeds via restriction of a space of events within a learning-specific action model. This way of learning closely resembles the well-known update method from dynamic epistemic logic. We introduce several different learning methods suited for finite identifiability of particular types of deterministic actions.
Original languageEnglish
Title of host publicationProceedings of the 5th International Workshop on Logic, Rationality, and Interaction (LORI 2015)
EditorsWiebe van der Hoek, Wesley H. Holliday, Wen-fang Wang
Publication date2015
ISBN (Print)978-3-662-48560-6
ISBN (Electronic)978-3-662-48561-3
Publication statusPublished - 2015
Event5th International Workshop on Logic, Rationality, and Interaction (LORI 2015) - Taipei, Taiwan, Province of China
Duration: 28 Oct 201531 Oct 2015
Conference number: 5


Conference5th International Workshop on Logic, Rationality, and Interaction (LORI 2015)
Country/TerritoryTaiwan, Province of China
Internet address
SeriesLecture Notes in Computer Science

Cite this