An Ensemble Architecture for Learning Complex Problem-Solving Techniques from Demonstration

No Thumbnail Available
Zhang, Xiaoqin
Shrestha, Bhavesh
Yoon, Sungwook
Kambhampati, Subbarao
DiBona, Phillip
Guo, Jinhong
McFarlane, Daniel
Hofmann, Martin
Whitebread, Kenneth
Appling, Darren
Issue Date
Research Projects
Organizational Units
Journal Issue
Alternative Title
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.
Full Citation
Transactions on Intelligent Systems and Technology
Terms of Use
PubMed ID