Instance-Based Parameter Tuning and Learning for Evolutionary AI Planning

Brendel Matthias 1 Marc Schoenauer 1
1 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 : Learn-and-Optimize (LaO) is a generic surrogate based method for parameter tuning combining learning and optimization. In this paper LaO is used to tune Divide-and-Evolve (DaE), an Evolutionary Algorithm for AI Planning. The LaO framework makes it possible to learn the relation between some features describing a given instance and the optimal parameters for this instance, thus it enables to extrapolate this relation to unknown instances in the same domain. Moreover, the learned model is used as a surrogate-model to accelerate the search for the optimal parameters. It hence becomes possible to solve intra-domain and extra-domain generalization in a single framework. The proposed implementation of LaO uses an Artificial Neural Network for learning the mapping between features and optimal parameters, and the Covariance Matrix Adaptation Evolution Strategy for optimization. Results demonstrate that LaO is capable of improving the quality of the DaE results even with only a few iterations. The main limitation of the DaE case-study is the limited amount of meaningful features that are available to describe the instances. However, the learned model reaches almost the same performance on the test instances, which means that it is capable of generalization.
Document type :
Conference papers
Complete list of metadatas

Cited literature [17 references]  Display  Hide  Download

https://hal.inria.fr/inria-00632368
Contributor : Brendel Matthias <>
Submitted on : Friday, October 14, 2011 - 11:02:34 AM
Last modification on : Monday, December 9, 2019 - 5:24:06 PM
Long-term archiving on: Tuesday, November 13, 2012 - 4:45:54 PM

File

icaps2011_cameraready.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00632368, version 1

Collections

Citation

Brendel Matthias, Marc Schoenauer. Instance-Based Parameter Tuning and Learning for Evolutionary AI Planning. 21st International Conference on Automated Planning and Scheduling, Planning and Learning Workshop, Jun 2011, Freiburg, Germany. ⟨inria-00632368⟩

Share

Metrics

Record views

152

Files downloads

734