Exploiting Macro-actions and Predicting Plan Length in Planning as Satisfiability

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 that have not been studied in this planning framework before: 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 and solver that can exploit macro actions and learned planning horizons to improve their performance. An experimental analysis illustrates the effectiveness of the proposed techniques.