Skip to Main content Skip to Navigation
Conference papers

Comment optimiser A* adaptatif

Lou Fedon 1, 2 Antoine Cornuéjols 3
1 TAO - Machine Learning and Optimisation
CNRS - Centre National de la Recherche Scientifique : UMR8623, Inria Saclay - Ile de France, UP11 - Université Paris-Sud - Paris 11, LRI - Laboratoire de Recherche en Informatique
Abstract : Efficient search of (quasi-)optimal paths in graphs remains a fundamental task in Artificial Intelligence. Recent works [7, 4, 5, 8] have contributed to a new point of view on this problem whereby heuristics are learned from past solving experiences rather than derived through a static abstraction of the description of the problem. In this paper, we show how to improve this work by better exploiting information from past solving episodes. The experiments reported here confirm the significant reduction in search space achieved by our algorithm. In a second part, we show how to generalize these learning techniques to the case of changing goal states. Extensive experiments and their analysis show that the variations of the goal states must obey strict laws in order for these adaptive A* algorithms to be advantageous.
Keywords : A Transfer Learning
Complete list of metadata

Cited literature [15 references]  Display  Hide  Download

https://hal.inria.fr/inria-00293136
Contributor : Lou Fedon <>
Submitted on : Thursday, July 3, 2008 - 4:45:49 PM
Last modification on : Thursday, July 8, 2021 - 3:47:59 AM
Long-term archiving on: : Monday, October 1, 2012 - 10:50:35 AM

File

Rfia08_ReverseAdaptiveA.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00293136, version 1
  • PRODINRA : 51293

Citation

Lou Fedon, Antoine Cornuéjols. Comment optimiser A* adaptatif. RFIA 2008: 16.Congrès Francophone AFRIF-AFIA. Reconnaissance des Formes et Intelligence Artificielle, Jan 2008, Amiens, France. 8 p. ⟨inria-00293136⟩

Share

Metrics

Record views

347

Files downloads

303