The use of automatically learned knowledge for a planning domain can significantly improve the performance of a generic planner when solving a problem in this domain. In this work, we focus on the well-known SAT-based approach to planning and investigate two types of learned knowledge: macro-actions and planning horizon. Macro-actions are sequences of actions that typically occur in the solution plans, while a planning horizon of a problem is the length of a (possibly optimal) plan solving it. We propose a method that uses a machine learning tool for building a predictive model of the optimal planning horizon, and variants of the well-known planner SatPlan and solver MiniSat that can exploit macro actions and learned planning horizons to improve their performance. An experimental analysis illustrates the effectiveness of the proposed techniques demonstrating that significant speedups can be obtained.
|Number of pages||22|
|Publication status||Published - Apr 2015|
|Event||19th RCRA International Workshop on "Experimental Evaluation of Algorithms for Solving Problems with Combinatorial Explosion" - Sapienza University, Rome, Italy|
Duration: 14 Jun 2012 → 15 Jun 2012
http://rcra.aixia.it/rcra2012/workshop-programme (Link to Workshop Programme)
Gerevini, A. E., Saetti, A., & Vallati, M. (2015). Exploiting macro-actions and predicting plan length in planning as satisfiability. AI Communications, 28(2), 323-344. https://doi.org/10.3233/AIC-140641