Title:
Multistrategy Learning Methods for Multirobot Systems
Multistrategy Learning Methods for Multirobot Systems
Author(s)
Arkin, Ronald C.
Endo, Yoichiro
Lee, Brian
MacKenzie, Douglas Christopher
Martinson, Eric
Endo, Yoichiro
Lee, Brian
MacKenzie, Douglas Christopher
Martinson, Eric
Advisor(s)
Editor(s)
Collections
Supplementary to
Permanent Link
Abstract
This article describes three different methods for introducing machine learning into a hybrid deliberative/reactive architecture for multirobot systems: learning momentum, Q-learning, and CBR wizards. A range of simulation experiments and results are reported using the Georgia Tech MissionLab mission specification system.
Sponsor
Date Issued
2003
Extent
Resource Type
Text
Resource Subtype
Paper