OREGON STATE UNIVERSITY

You are here

An Ensemble Learning and Problem-Solving Architecture for Airspace Management

TitleAn Ensemble Learning and Problem-Solving Architecture for Airspace Management
Publication TypeConference Paper
Year of Publication2009
AuthorsZhang, X., S. Yoon, P. DiBona, D S. Appling, L. Ding, J R. Doppa, D. Green, J. K. Guo, U. Kuter, G. Levine, R. L. MacTavish, D. McFarlane, J. R. Michaelis, H. Mostafa, S. Ontanon, C. Parker, J. Radhakrishnan, A. Rebguns, B. Shrestha, Z. Song, E. B. Trewhitt, H. Zafar, C. Zhang, D. Corkill, G. DeJong, T. G. Dietterich, S. Kambhampati, V. Lesser, D. L. McGuinness, A. Ram, D. Spears, P. Tadepalli, E. T. Whitaker, W-K. Wong, J. A. Hendler, M. O. Hofmann, and K. Whitebread
Conference NameProceedings of Twenty-First Annual Conference on Innovative Applications of Artificial Intelligence (IAAI-09)
Pagination203-210
Date Published07/2009
Conference LocationPasadena, CA
Abstract

In this paper we describe the application of a novel learning and problem solving architecture to the domain of airspace management, where multiple requests for the use of airspace need to be reconciled and managed automatically. The key feature of our “Generalized Integrated Learning Architecture” (GILA) is a set of integrated learning and reasoning (ILR) systems coordinated by a central meta-reasoning executive (MRE). Each ILR learns independently from the same training example and contributes to problem-solving in concert with other ILRs as directed by the MRE. Formal evaluations show that our system performs as well as or better than humans after learning from the same training data. Further, GILA outperforms any individual ILR run in isolation, thus demonstrating the power of the ensemble architecture for learning and problem solving.

URLhttp://mas.cs.umass.edu/paper/468