Show simple item record

dc.contributor.advisorHayes, Gillianen
dc.contributor.advisorHallam, Johnen
dc.contributor.authorWyatt, Jeremyen
dc.date.accessioned2004-06-17T15:02:09Z
dc.date.available2004-06-17T15:02:09Z
dc.date.issued1998-07
dc.identifier.urihttp://hdl.handle.net/1842/532
dc.descriptionInstitute of Perception, Action and Behaviouren
dc.description.abstractRecently there has been a good deal of interest in using techniques developed for learning from reinforcement to guide learning in robots. Motivated by the desire to find better robot learning methods, this thesis prsents a number of novel extensions to existing techniques for controlling exploration and inference in reinforcement learning. First I distinguish between the well known exploration-exploitation trade-off and what I term exploration for future exploitation. it is argued that there are many tasks where it is more appropriate to maximise this latter measure. In particular it is appropriate when we want to employ learning algorithms as part of the process of designing a controller.Informed by this insight I develop a number of novel measures of the probability of a particular course of action being the optimal ourse of action. Estimators are developed for this measure for boolean and non-boolean processes. These are used in turn to develp probability matching techniques for guiding the exploration-exploitation trade-off. A proof is presented that one such method will converge in the limit to the optimal policy. Following this I develop an engropic measure of task-knowledg, based on the previous measure.en
dc.contributor.sponsorEngineering and Physical Sciences Research Council (EPSRC)en
dc.format.extent2142153 bytesen
dc.format.extent1089571 bytesen
dc.format.mimetypeapplication/postscripten
dc.format.mimetypeapplication/pdfen
dc.language.isoen
dc.publisherUniversity of Edinburgh. College of Science and Engineering. School of Informatics.en
dc.titleExploration and Inference in Learning from Reinforcementen
dc.typeThesis or Dissertationen
dc.type.qualificationlevelDoctoralen
dc.type.qualificationnamePhD Doctor of Philosophyen


Files in this item

This item appears in the following Collection(s)

Show simple item record