Show simple item record

dc.rights.licenseRestricted to current Rensselaer faculty, staff and students. Access inquiries may be directed to the Rensselaer Libraries.
dc.contributorEmbrechts, Mark J.
dc.contributorBonissone, Piero P.
dc.contributorDunn, Stanley
dc.contributorMendonça, David
dc.contributorWillemain, Thomas R.
dc.contributor.authorGatti, Christopher J.
dc.date.accessioned2021-11-03T08:13:49Z
dc.date.available2021-11-03T08:13:49Z
dc.date.created2014-10-08T11:04:57Z
dc.date.issued2014-08
dc.identifier.urihttps://hdl.handle.net/20.500.13015/1193
dc.descriptionAugust 2014
dc.descriptionSchool of Engineering
dc.description.abstractReinforcement learning is one of the fundamental learning techniques that humans use to learn how to interact with and make decisions within challenging or uncertain environments. In essence, it is based on an iterative process of trial-and-error, and learning from both positive and negative feedback. This learning paradigm also serves as the basis for a machine learning technique that can be used to solve sequential decision making problems by learning a sequence of actions to achieve a goal or maximize performance. As a machine learning method, this method was developed decades ago and there have been numerous variations and developments. However, extending these methods to real-world challenging problems is often not successful, and there are relatively few noteworthy applications. Furthermore, the reasons behind successful applications are not completely understood.
dc.description.abstractThe purpose of this work is to gain a better understanding of reinforcement learning in a variety of problems. We are interested in fundamental knowledge, basic science if you will, of what affects reinforcement learning and what contributes to a successful implementation. This work takes an empirical approach to understanding the behavior and interactions between the two main components of reinforcement learning: the learning algorithm and the functional representation of the learned knowledge. We study these entities using an approach that is not commonly employed to study machine learning methods, that being design of experiments. We use contemporary design of experiments methods, including a novel sequential experimentation procedure that finds convergent learning algorithm parameter subregions, and stochastic kriging for response surface metamodeling. We consider three problems in this work, one benchmark reinforcement learning problem and two more real world and challenging problems: the mountain car problem, the truck backer-upper problem, and the tandem truck backer-upper problem. The knowledge gained from this work provides insight as to what enables and what has an effect on successful reinforcement learning implementations so that this learning method can be applied to more challenging problems.
dc.language.isoENG
dc.publisherRensselaer Polytechnic Institute, Troy, NY
dc.relation.ispartofRensselaer Theses and Dissertations Online Collection
dc.subjectDecision sciences and engineering systems
dc.titleDesign of experiments for reinforcement learning
dc.typeElectronic thesis
dc.typeThesis
dc.digitool.pid173005
dc.digitool.pid173006
dc.digitool.pid173007
dc.rights.holderThis electronic version is a licensed copy owned by Rensselaer Polytechnic Institute, Troy, NY. Copyright of original work retained by author.
dc.description.degreePhD
dc.relation.departmentDept. of Industrial and Systems Engineering


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record