Abstract
The beliefs of an agent change in response to new information. Formal belief change operators have been introduced to model this change. Although the properties of belief change operators are well understood, there has been little work on specifying exactly where these operators come from. In this paper, we propose that belief revision operators can be learned from data. In other words, by looking at the behaviour of an agent, we can use basic machine learning algorithms to determine exactly how they revise their beliefs. This is a preliminary paper advocating a particular approach, and demonstrating its feasibility. Fundamentally, we are concerned with the manner in which machine learning techniques can be used to learn formal models of knowledge and belief. We suggest that this kind of advance will be important for future applications of AI.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alchourrón, C.E., Gärdenfors, P., Makinson, D.: On the logic of theory change: partial meet functions for contraction and revision. J. Symbolic Logic 50(2), 510–530 (1985)
Katsuno, H., Mendelzon, A.O.: Propositional knowledge base revision and minimal change. Artif. Intell. 52(3), 263–294 (1992)
Liberatore, P.: Revision by history. J. Artif. Intell. Res. 52, 287–329 (2015)
Luo, W., Schulte, O.: Mind change efficient learning. Inf. Comput. 204(6), 989–1011 (2006)
McCarthy, J., Lifschitz, V.: Formalizing Commonsense: Papers by John McCarthy. Greenwood Publishing Group Inc., Westport (1990)
Mitchell, T.: Machine Learning. McGraw Hill, New York (1997)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Hunter, A. (2018). Learning Belief Revision Operators. In: Bagheri, E., Cheung, J. (eds) Advances in Artificial Intelligence. Canadian AI 2018. Lecture Notes in Computer Science(), vol 10832. Springer, Cham. https://doi.org/10.1007/978-3-319-89656-4_21
Download citation
DOI: https://doi.org/10.1007/978-3-319-89656-4_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-89655-7
Online ISBN: 978-3-319-89656-4
eBook Packages: Computer ScienceComputer Science (R0)