2015/07/15 by Thomas Bolander, Bolander, Thomas, Nina Gierasimczuk +1
Computer Science · #AI-based Problem Solving and Planning #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Logic in Computer Science (cs.LO) #Logic, Reasoning, and Knowledge #Machine Learning (cs.LG) #Semantic Web and Ontologies #cs.AI #cs.LG #cs.LO
paper · pdf · doi:10.48550/arxiv.1507.04285
18 pages, accepted for LORI-V: The Fifth International Conference on Logic, Rationality and Interaction, October 28-31, 2015, National Taiwan University, Taipei, Taiwan
arxiv created 2015/07/15 · openalex publication_date 2015/07/15 · arxiv updated 2015/07/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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.