Belief Revision Operators with Varying Attitudes Towards Initial Beliefs

Belief Revision Operators with Varying Attitudes Towards Initial Beliefs

Adrian Haret, Stefan Woltran

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence
Main track. Pages 1726-1733. https://doi.org/10.24963/ijcai.2019/239

Classical axiomatizations of belief revision include a postulate stating that if new information is consistent with initial beliefs, then revision amounts to simply adding the new information to the original knowledge base. This postulate assumes a conservative attitude towards initial beliefs, in the sense that an agent faced with the need to revise them will seek to preserve initial beliefs as much as possible. In this work we look at operators that can assume different attitudes towards original beliefs. We provide axiomatizations of these operators by varying the aforementioned postulate and obtain representation results that characterize the new types of operators using preorders on possible worlds. We also present concrete examples for each new type of operator, adapting notions from decision theory.
Keywords:
Knowledge Representation and Reasoning: Belief Change
Knowledge Representation and Reasoning: Reasoning about Knowlege and Belief