Publication: Performance modelling of planners from homogeneous problem sets
Loading...
Identifiers
Publication date
2017-06-18
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
Aaai Press. Association For The Advancement Of Artificial Intelligence
Impact
Export
Abstract
Empirical performance models play an important role in the development of planning portfolios that make a per-domain or per-problem configuration of its search components. Even though such portfolios have shown their power when compared to other systems in current benchmarks, there is no clear evidence that they are capable to differentiate problems (instances) having similar input properties (in terms of objects, goals, etc.) but fairly different runtime for a given planner. In this paper we present a study of empirical performance models that are trained using problems having the same configuration, with the objective of guiding the models to recognize the underlying differences existing among homogeneous problems. In addition we propose a set of new features that boost the prediction capabilities under such scenarios. The results show that the learned models clearly performed over random classifiers, which reinforces the hypothesis that the selection of planners can be done on a per-instance basis when configuring a portfolio.
Description
Keywords
Bibliographic citation
Fernandez Rebollo, Fernando; De La Rosa Turbides, Tomas Eduardo; Cenamor Guijarro, Isabel Rosario (2017). Performance modelling of planners from homogeneous problem sets. Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling (ICAPS 2017). : Aaai Press. Association For The Advancement Of Artificial Intelligence . Pp. 425-433