Learning Generalized Policies from Planning Examples Using Concept Languages

91 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Learning First-Order Symbolic Representations for Planning from the Structure of the State Space (2019, methodology): “ymbolic language, or with information about the actions and their arguments [11]. Inductive logic programming methods [31] have been used for learning general policies but from symbolic encodings too [23, 28, 14]. More recently, general policies have been learned using deep learning methods but also”
A review of generalized planning (2019, methodology): “This is what happens in Finite State Controllers (FSCs) [10], generalized policies [57], or with the conditional gotos used in planning programs [83].”
Learning Features and Abstract Actions for Computing Generalized Plans (2018, methodology): “Description logics have been used for capturing general policies using purely learning methods (Martı́n and Geffner 2004; Fern, Yoon, and Givan 2006).”
Learning Generalized Reactive Policies using Deep Neural Networks (2017, methodology): “Martin, M., and Geffner, H. 2000.”