[full paper] |
David Lorenzo, Ramon P. Otero
We focus on learning representations of dynamical systems that can be characterized by logic-based formalisms for reasoning about actions and change, where system's behaviours are naturally viewed as appropiate logical consequences of the domain's description. To this end, Inductive Logic Programming is reformulated using Logic Programming for dynamic systems. The study of dynamic domains is started with domains modelable with classical action theories and is progressively enhanced to manage more complex behaviours.
Keywords: Machine Learning, Reasoning about actions and change, Inductive logic Programming, Cognitive Robotics
Citation: David Lorenzo, Ramon P. Otero: Learning to Reason About Actions. In W.Horn (ed.): ECAI2000, Proceedings of the 14th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2000, pp.316-320.