Deep Learning of Heuristics for Domain-independent Planning

: Automated planning deals with the problem of finding a sequence of actions leading from a given state to a desired state. The state-of-the-art automated planning techniques exploit informed forward search guided by a heuristic, where the heuristic (under)estimates a distance from a state to a goal state. In this paper, we present a technique to automatically construct an efficient heuristic for a given domain. The proposed approach is based on training a deep neural network using a set of solved planning problems from the domain. We use a novel way of generating features for states which doesn’t depend on usage of existing heuristics. The trained network can be used as a heuristic on any problem from the domain of interest without any limitation on the problem size. Our experiments show that the technique is competitive with popular domain-independent heuristic.

[1]  Susanne Biundo-Stephan,et al.  On Guiding Search in HTN Planning with Classical Planning Heuristics , 2019, IJCAI.

[2]  Dong Tian,et al.  Learning Heuristic Functions for Mobile Robot Path Planning Using Deep Neural Networks , 2019, ICAPS.

[3]  Leslie Pack Kaelbling,et al.  From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning , 2018, J. Artif. Intell. Res..

[4]  Pieter Abbeel,et al.  Learning Generalized Reactive Policies using Deep Neural Networks , 2017, ICAPS.

[5]  Meng Zhang,et al.  Neural Network Methods for Natural Language Processing , 2017, Computational Linguistics.

[6]  Otakar Trunda,et al.  Deep Heuristic-learning in the Rubik's Cube Domain: An Experimental Evaluation , 2017, ITAT.

[7]  Martin Wehrle,et al.  Learning Heuristic Functions in Classical Planning , 2016 .

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  Hugo Larochelle,et al.  Using a Recursive Neural Network to Learn an Agent's Decision Model for Plan Recognition , 2015, IJCAI.

[10]  Fernando Fernández,et al.  Learning Predictive Models to Configure Planning Portfolios , 2013 .

[11]  Sergio Jiménez Celorrio,et al.  A review of machine learning for automated planning , 2012, The Knowledge Engineering Review.

[12]  Sandra Zilles,et al.  Learning heuristic functions for large state spaces , 2011, Artif. Intell..

[13]  Jyh-Da Wei,et al.  Using Neural Networks for Evaluation in Heuristic Search Algorithm , 2011, AAAI.

[14]  Wheeler Ruml,et al.  Learning Inadmissible Heuristics During Search , 2011, ICAPS.

[15]  Sandra Zilles,et al.  Bootstrap Learning of Heuristic Functions , 2010, SOCS.

[16]  Jonathan Schaeffer,et al.  Learning from Multiple Heuristics , 2008, AAAI.

[17]  Robert Givan,et al.  Learning Control Knowledge for Forward Search Planning , 2008, J. Mach. Learn. Res..

[18]  Michael Fink,et al.  Online Learning of Search Heuristics , 2007, AISTATS.

[19]  Paolo Traverso,et al.  Automated Planning: Theory & Practice , 2004 .

[20]  Hector Geffner,et al.  Learning Generalized Policies from Planning Examples Using Concept Languages , 2004, Applied Intelligence.

[21]  Eric R. Ziegel,et al.  The Elements of Statistical Learning , 2003, Technometrics.

[22]  Bernhard Nebel,et al.  The FF Planning System: Fast Plan Generation Through Heuristic Search , 2011, J. Artif. Intell. Res..

[23]  Judea Pearl,et al.  Heuristics : intelligent search strategies for computer problem solving , 1984 .

[24]  Jesfis Peral,et al.  Heuristics -- intelligent search strategies for computer problem solving , 1984 .