Inductive Learning of Answer Set Programs
Existing work on Inductive Logic Programming (ILP) has focused mainly on the learning of definite programs or normal logic programs. In this paper, we aim to push the computational boundary to a wider class of programs: Answer Set Programs. We propose a new paradigm for ILP that integrates existing notions of brave and cautious semantics within a unifying learning framework whose inductive solutions are Answer Set Programs and examples are partial interpretations We present an algorithm that is sound and complete with respect to our new notion of inductive solutions. We demonstrate its applicability by discussing a prototype implementation, called ILASP (Inductive Learning of Answer Set Programs), and evaluate its use in the context of planning. In particular, we show how ILASP can be used to learn agent’s knowledge about the environment. Solutions of the learned ASP program provide plans for the agent to travel through the given environment.
KeywordsInductive Reasoning Learning Answer Set Programs Nonmonotonic Inductive Logic Programming
Unable to display preview. Download preview PDF.
- 1.Corapi, D., Russo, A., Lupu, E.: Inductive logic programming as abductive search. In: ICLP (Technical Communications), pp. 54–63 (2010)Google Scholar
- 5.Gebser, M., Kaminski, R., Kaufmann, B., Schaub, T.: Answer Set Solving in Practice. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan and Claypool Publishers (2012)Google Scholar
- 6.Gelfond, M., Lifschitz, V.: The stable model semantics for logic programming. In: ICLP/SLP, vol. 88, pp. 1070–1080 (1988)Google Scholar
- 9.Law, M., Russo, A., Broda, K.: Proofs for inductive learning of answer set programs, https://www.doc.ic.ac.uk/~ml1909/ILASP_Proofs.pdf
- 12.Muggleton, S., Lin, D.: Meta-interpretive learning of higher-order dyadic datalog: Predicate invention revisited. In: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, pp. 1551–1557. AAAI Press (2013)Google Scholar