Learning Divide-and-Evolve Parameter Configurations with Racing

Jacques Bibai 1, 2 Pierre Savéant 1 Marc Schoenauer 2 Vincent Vidal 3
2 TAO - Machine Learning and Optimisation
LRI - Laboratoire de Recherche en Informatique, UP11 - Université Paris-Sud - Paris 11, Inria Saclay - Ile de France, CNRS - Centre National de la Recherche Scientifique : UMR8623
Abstract : The sub-optimal DAE planner implements the stochastic approach for domain-independent planning decomposition introduced in (Schoenauer, Sav´eant, and Vidal 2006; 2007). This planner optimizes either the makespan or the number of actions by generating ordered sequences of intermediate goals via a process of artificial evolution. The evolutionary part of DAE uses the Evolving Objects (EO) library, and the embedded planner it is based on is the non-optimal STRIPS planner YAHSP (Vidal 2004). For a given domain, the learning phase uses a racing procedure to choose the rates of the different variation operators used in DAE, and processes the results obtained during this process to specify the predicates that will be later used to describe the intermediate goals.
Document type :
Conference papers
Complete list of metadatas

Cited literature [8 references]  Display  Hide  Download

https://hal.inria.fr/inria-00406626
Contributor : Jacques Bibai <>
Submitted on : Friday, February 12, 2010 - 5:36:26 PM
Last modification on : Monday, December 9, 2019 - 5:24:06 PM
Long-term archiving on: Tuesday, June 15, 2010 - 9:15:10 PM

File

ICAPS09-Workshop_on_planning_a...
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00406626, version 1

Collections

Citation

Jacques Bibai, Pierre Savéant, Marc Schoenauer, Vincent Vidal. Learning Divide-and-Evolve Parameter Configurations with Racing. ICAPS-09-Workshop on Planning and Learning, ICAPS and University of Macedonia, Sep 2009, Thessaloniki, Greece. ⟨inria-00406626⟩

Share

Metrics

Record views

316

Files downloads

796