An ensemble architecture for learning complex problem-solving techniques from demonstration

Xiaoqin Shelley Zhang, Bhavesh Shrestha, Sungwook Yoon, Subbarao Kambhampati, Phillip Dibona, Jinhong K. Guo, Daniel McFarlane, Martin O. Hofmann, Kenneth Whitebread, Darren Scott Appling, Elizabeth T. Whitaker, Ethan B. Trewhitt, Li Ding, James R. Michaelis, Deborah L. McGuinness, James A. Hendler, Janardhan Rao Doppa, Charles Parker, Thomas G. Dietterich, Prasad TadepalliWeng Keen Wong, Derek Green, Anton Rebguns, Diana Spears, Ugur Kuter, Geoff Levine, Gerald Dejong, Reid L. MacTavish, Santiago Ontañón, Jainarayan Radhakrishnan, Ashwin Ram, Hala Mostafa, Huzaifa Zafar, Chongjie Zhang, Daniel Corkill, Victor Lesser, Zhexuan Song

Research output: Contribution to journalArticlepeer-review

Abstract

We present a novel ensemble architecture for learning problem-solving techniques from a very small number of expert solutions and demonstrate its effectiveness in a complex real-world domain. The key feature of our "Generalized Integrated Learning Architecture" (GILA) is a set of heterogeneous independent learning and reasoning (ILR) components, coordinated by a central meta-reasoning executive (MRE). The ILRs are weakly coupled in the sense that all coordination during learning and performance happens through the MRE. Each ILR learns independently from a small number of expert demonstrations of a complex task. During performance, each ILR proposes partial solutions to subproblems posed by the MRE, which are then selected from and pieced together by the MRE to produce a complete solution. The heterogeneity of the learner-reasoners allows both learning and problem solving to be more effective because their abilities and biases are complementary and synergistic. We describe the application of this novel learning and problem solving architecture to the domain of airspace management, where multiple requests for the use of airspaces need to be deconflicted, reconciled, and managed automatically. Formal evaluations show that our system performs as well as or better than humans after learning from the same training data. Furthermore, GILA outperforms any individual ILR run in isolation, thus demonstrating the power of the ensemble architecture for learning and problem solving.

Original languageEnglish (US)
Article number75
JournalACM Transactions on Intelligent Systems and Technology
Volume3
Issue number4
DOIs
StatePublished - Sep 2012

Keywords

  • Complex problemsolving
  • Ensemble architecture
  • Learning from demonstration

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'An ensemble architecture for learning complex problem-solving techniques from demonstration'. Together they form a unique fingerprint.

Cite this