Can Doxastic Agents Learn? On the Temporal Structure of Learning

Formal learning theory formalizes the phenomenon of language acquisition. The theory focuses on various properties of the process of conjecture-change over time, and therefore it is also applicable in philosophy of science, where it can be interpreted as a theory of empirical inquiry. Treating "conjectures" as beliefs, we link the process of conjecture-change to doxastic update. Using this approach, we reconstruct and analyze the temporal aspect of learning in the context of temporal and dynamic logics of belief change. We provide a translation of learning scenarios into the domain of dynamic doxastic epistemic logic. Then, we express the problem of finite identifiability as a problem of epistemic temporal logic model checking. Furthermore, we prove a doxastic epistemic temporal logic representation result corresponding to an important theorem from learning theory, that characterizes identifiability in the limit, namely Angluin's theorem. In the end we discuss consequences and possible extensions of our work.

[1]  Lawrence S. Moss,et al.  Logics for Epistemic Programs , 2004, Synthese.

[2]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[3]  Dana Angluin,et al.  Inductive Inference of Formal Languages from Positive Data , 1980, Inf. Control..

[4]  Lawrence S. Moss,et al.  The Logic of Public Announcements and Common Knowledge and Private Suspicions , 1998, TARK.

[5]  Nina Gierasimczuk Bridging learning theory and dynamic epistemic logic , 2009, Synthese.

[6]  Ronald Fagin,et al.  Reasoning about knowledge , 1995 .

[7]  D. N. Pritt From Right to Left , 1965 .

[8]  Ramaswamy Ramanujam,et al.  A Knowledge Based Semantics of Messages , 2003, J. Log. Lang. Inf..

[9]  Johan van Benthem,et al.  Merging Frameworks for Interaction , 2009, J. Philos. Log..

[10]  Klaus P. Jantke,et al.  Analogical and Inductive Inference , 1986, Lecture Notes in Computer Science.

[11]  Alexandru Baltag,et al.  A qualitative theory of dynamic interactive belief revision , 2008 .

[12]  Yasuhito Mukouchi,et al.  Characterization of Finite Identification , 1992, AII.

[13]  Ron van der Meyden,et al.  Complete Axiomatizations for Reasoning about Knowledge and Branching Time , 2003, Stud Logica.

[14]  Rolf Wiehagen,et al.  Learning by Erasing , 1996, ALT.

[15]  Joseph Y. Halpern,et al.  Modeling Belief in Dynamic Systems, Part I: Foundations , 1997, Artif. Intell..

[16]  Johan van Benthem,et al.  Merging frameworks for interaction: DEL and ETL , 2007, TARK '07.

[17]  B. T. Cate,et al.  Model theory for extended modal languages , 2005 .