Show simple item record

dc.contributor.authorZhang, Xiaoqin
dc.contributor.authorShrestha, Bhavesh
dc.contributor.authorYoon, Sungwook
dc.contributor.authorKambhampati, Subbarao
dc.contributor.authorDiBona, Phillip
dc.contributor.authorGuo, Jinhong
dc.contributor.authorMcFarlane, Daniel
dc.contributor.authorHofmann, Martin
dc.contributor.authorWhitebread, Kenneth
dc.contributor.authorAppling, Darren
dc.contributor.authorWhitaker, Elizabeth
dc.contributor.authorTrewhitt, Ethan
dc.contributor.authorDing, Li
dc.contributor.authorMichaelis, James
dc.contributor.authorMcGuinness, Deborah L.
dc.contributor.authorHendler, James A.
dc.contributor.authorDoppa, Janardhan
dc.contributor.authorParker, Charles
dc.contributor.authorDietterich, Thomas
dc.contributor.authorTadepalli, Prasad
dc.contributor.authorWong, Weng-Keen
dc.contributor.authorGreen, Derek
dc.contributor.authorRebguns, Anton
dc.contributor.authorSpears, Diana
dc.contributor.authorKuter, Ugur
dc.contributor.authorLevine, Geoff
dc.contributor.authorDeJong, Gerald
dc.contributor.authorMacTavish, Reid
dc.contributor.authorOntanon, Santiago
dc.contributor.authorRadhakrishnan, Jainarayan
dc.contributor.authorRam, Ashwin
dc.contributor.authorMostafa, Hala
dc.contributor.authorZafar, Huzaifa
dc.contributor.authorZhang, Chongjie
dc.contributor.authorCorkill, Daniel
dc.contributor.authorLesser, Victor
dc.contributor.authorSong, Zhexuan
dc.date.accessioned2022-02-18T02:37:14Z
dc.date.available2022-02-18T02:37:14Z
dc.date.issued2012-09-01
dc.identifier.other158
dc.identifier.urihttp://archive.tw.rpi.edu/media/latest/TIST-Integrated-Learning.pdf
dc.identifier.urihttps://hdl.handle.net/20.500.13015/4560
dc.description.abstractWe 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.
dc.publisherTransactions on Intelligent Systems and Technology
dc.relation.ispartofseries3
dc.relation.ispartofseries4
dc.titleAn Ensemble Architecture for Learning Complex Problem-Solving Techniques from Demonstration


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record