Repository logo
 

A synthesis of reinforcement learning and robust control theory

Simple item page
dc.contributor.authorKretchmar, R. Matthew, author
dc.contributor.authorAnderson, Charles, advisor
dc.contributor.authorHowe, Adele E., committee member
dc.contributor.authorWhitley, L. Darrell, committee member
dc.contributor.authorYoung, Peter M., committee member
dc.contributor.authorHittle, Douglas C., committee member
dc.date.accessioned2007-01-03T04:43:07Z
dc.date.available2007-01-03T04:43:07Z
dc.date.issued2000
dc.descriptionDepartment Head: Stephen B. Seidman.
dc.description.abstractThe pursuit of control algorithms with improved performance drives the entire control research community as well as large parts of the mathematics, engineering, and artificial intelligence research communities. A fundamental limitation on achieving control performance is the conflicting requirement of maintaining system stability. In general, the more aggressive is the controller, the better the control performance but also the closer to system instability. Robust control is a collection of theories, techniques, the tools that form one of the leading edge approaches to control. Most controllers are designed not on the physical plant to be controlled, but on a mathematical model of the plant; hence, these controllers often do not perform well on the physical plant and are sometimes unstable. Robust control overcomes this problem by adding uncertainty to the mathematical model. The result is a more general, less aggressive controller which performs well on the both the model and the physical plant. However, the robust control method also sacrifices some control performance in order to achieve its guarantees of stability. Reinforcement learning based neural networks offer some distinct advantages for improving control performance. Their nonlinearity enables the neural network to implement a wider range of control functions, and their adaptability permits them to improve control performance via on-line, trial-and-error learning. However, neuro-control is typically plagued by a lack of stability guarantees. Even momentary instability cannot be tolerated in most physical plants, and thus, the threat of instability prohibits the application of neuro-control in many situations. In this dissertation, we develop a stable neuro-control scheme by synthesizing the two fields of reinforcement learning and robust control theory. We provide a learning system with many of the advantages of neuro-control. Using functional uncertainty to represent the nonlinear and time-varying components of the neuro networks, we apply the robust control techniques to guarantee the stability of our neuro-controller. Our scheme provides stable control not only for a specific fixed-weight, neural network, but also for a neuro-controller in which the weights are changing during learning. Furthermore, we apply our stable neuro-controller to several control tasks to demonstrate that the theoretical stability guarantee is readily applicable to real-life control situations. We also discuss several problems we encounter and identify potential avenues of future research.
dc.format.mediumdoctoral dissertations
dc.identifier2000_summer_Kretchmar_COMS.pdf
dc.identifierETDF2000100002COMS
dc.identifier.urihttp://hdl.handle.net/10217/26305
dc.languageEnglish
dc.language.isoeng
dc.publisherColorado State University. Libraries
dc.relationCatalog record number (MMS ID): 991009402799703361
dc.relationQ325.6.K74 2000
dc.relation.ispartof2000-2019
dc.rightsCopyright and other restrictions may apply. User is responsible for compliance with all applicable laws. For information about copyright law, please see https://libguides.colostate.edu/copyright.
dc.subjectrobust control theory
dc.subjectneuro-control scheme
dc.subjectneuro-controller
dc.subjectneural networks
dc.subject.lcshReinforcement learning
dc.subject.lcshControl theory
dc.titleA synthesis of reinforcement learning and robust control theory
dc.typeText
dcterms.rights.dplaThis Item is protected by copyright and/or related rights (https://rightsstatements.org/vocab/InC/1.0/). You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
thesis.degree.disciplineComputer Science
thesis.degree.grantorColorado State University
thesis.degree.levelDoctoral
thesis.degree.nameDoctor of Philosophy (Ph.D.)

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
2000_summer_Kretchmar_COMS.pdf
Size:
1.12 MB
Format:
Adobe Portable Document Format
Description:
Download

Collections

2000-2019
Theses and Dissertations