Show simple item record

dc.contributor.authorMehta, Tejas R.
dc.contributor.authorEgerstedt, Magnus B.
dc.date.accessioned2011-04-12T16:02:24Z
dc.date.available2011-04-12T16:02:24Z
dc.date.issued2005-03
dc.identifier.citationT. Mehta and M. Egerstedt. Learning Multi-Modal Control Programs. Hybrid Systems: Computation and Control, Springer-Verlag, Zurich, Switzerland, March 2005.en_US
dc.identifier.isbn978-3-540-25108-8
dc.identifier.urihttp://hdl.handle.net/1853/38480
dc.descriptionThe original publication is available at www.springerlink.com.en_US
dc.description.abstractMulti-modal control is a commonly used design tool for breaking up complex control tasks into sequences of simpler tasks. In this paper, we show that by viewing the control space as a set of such tokenized instructions rather than as real-valued signals, reinforcement learning becomes applicable to continuous-time control systems. In fact, we show how a combination of state-space exploration and multi-modal control converts the original system into a finite state machine, on which Q-learning can be utilized.en_US
dc.language.isoen_USen_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectMulti-modal controlen_US
dc.subjectState-space explorationen_US
dc.subjectLearning techniquesen_US
dc.titleLearning Multi-Modal Control Programsen_US
dc.typeBook chapteren_US
dc.contributor.corporatenameGeorgia Institute of Technology. School of Electrical and Computer Engineering
dc.contributor.corporatenameGeorgia Institute of Technology. Center for Robotics and Intelligent Machines
dc.publisher.originalSpringer-Verlag


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record