Automatic configuration of sequential planning portfolios

Seipp, Jendrik and Sievers, Silvan and Helmert, Malte and Hutter, Frank. (2015) Automatic configuration of sequential planning portfolios. In: Proceedings of the 29th AAAI Conference on Artificial Intelligence (AAAI 2015) : January 25 –30, 2015, Austin, Texas, USA. Palo Alto, Calif., pp. 3364-3370.

PDF - Published Version

Official URL: http://edoc.unibas.ch/dok/A6373491

Downloads: Statistics Overview


Sequential planning portfolios exploit the complementary strengths of different planners. Similarly, automated algorithm configuration tools can customize parameterized planning algorithms for a given type of tasks. Although some work has been done towards combining portfolios and algorithm configuration, the problem of automatically generating a sequential planning portfolio from a parameterized plan- ner for a given type of tasks is still largely unsolved. Here, we present Cedalion, a conceptually simple approach for this problem that greedily searches for the h parameter configu- ration, runtime i pair which, when appended to the current portfolio, maximizes portfolio improvement per additional runtime spent. We show theoretically that Cedalion yields portfolios provably within a constant factor of optimal for the training set distribution. We evaluate Cedalion empirically by applying it to construct sequential planning portfolios based on component planners from the highly parameterized Fast Downward (FD) framework. Results for a broad range of planning settings demonstrate that – without any knowledge of planning or FD – Cedalion constructs sequential FD port- folios that rival, and in some cases substantially outperform, manually-built FD portfolios.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Artificial Intelligence (Helmert)
UniBasel Contributors:Seipp, Jendrik and Helmert, Malte and Sievers, Silvan
Item Type:Conference or Workshop Item, refereed
Conference or workshop item Subtype:Conference Paper
Publisher:AAAI Press
Note:Publication type according to Uni Basel Research Database: Conference paper
Related URLs:
edoc DOI:
Last Modified:20 Nov 2018 09:23
Deposited On:05 Jun 2015 08:52

Repository Staff Only: item control page