Non-Expansive Fuzzy Coalgebraic Logic

Abstract

Fuzzy logic extends the classical truth values "true" and "false" with additional truth degrees in between. More specifically, fuzzy modal logics in this sense are given by a choice of fuzzy modalities and a fuzzy propositional base. It has been noted that fuzzy modal logics over the Zadeh base, which interprets disjunction as maximum, are often computationally tractable but on the other hand add little in the way of expressivity to their classical counterparts. Contrastingly, fuzzy modal logics over the more expressive Lukasiewicz base have attractive logical properties but are often computationally less tractable or even undecidable. In the basic case of the modal logic of fuzzy relations, sometimes termed fuzzy ALC, it has recently been shown that an intermediate non-expansive propositional base, known from characteristic logics for behavioural distances of quantitative systems, strikes a balance between these poles: It provides increased expressiveness over the Zadeh base while avoiding the computational problems of the Lukasiewicz base, in fact allowing for reasoning in PSpace. Modal logics, in particular fuzzy modal logics, generally vary widely in terms of syntax and semantics, involving, for instance, probabilistic, preferential, or weighted structures. Coalgebraic modal logic provides a unifying framework for wide ranges of semantically different modal logics, both two-valued and fuzzy. In the present work, we focus on non-expansive coalgebraic fuzzy modal logics, providing a criterion for decidability in PSpace. Using this criterion, we recover the mentioned complexity result for non-expansive fuzzy ALC and moreover obtain new PSpace upper bounds for various quantitative modal logics over probabilistic and metric transition systems. Notably, we show that the logic of generally, which has recently been shown to characterize e-distance on Markov chains, is decidable in PSpace.