dc.creator | Conn, Karla Gail | |
dc.date.accessioned | 2020-08-22T20:36:20Z | |
dc.date.available | 2006-07-28 | |
dc.date.issued | 2005-07-28 | |
dc.identifier.uri | https://etd.library.vanderbilt.edu/etd-07272005-114235 | |
dc.identifier.uri | http://hdl.handle.net/1803/13631 | |
dc.description.abstract | This research measures how well supervised-reinforcement-learning techniques perform when applied to real-world tasks, managed as a discrete-event dynamic system (DEDS). Two types of experiments are tested. One tests the robot’s stability in implementing a task it has been taught. The other experiment includes obstacles blocking the path to the goal and measures the robot’s flexibility. The supervisor consists of human-guided remote-controlled runs through the navigation task and acts as a teacher for the initial stages of reinforcement learning. Experimental analysis is based on measurements of average time to reach the goal and the number of failed states encountered during a trial of episodes. | |
dc.format.mimetype | application/pdf | |
dc.subject | reinforcement learning | |
dc.subject | mobile robot | |
dc.subject | intelligent machine | |
dc.title | Supervised-reinforcement learning for a mobile robot in a real-world environment | |
dc.type | thesis | |
dc.contributor.committeeMember | Douglas Fisher | |
dc.type.material | text | |
thesis.degree.name | MS | |
thesis.degree.level | thesis | |
thesis.degree.discipline | Electrical Engineering | |
thesis.degree.grantor | Vanderbilt University | |
local.embargo.terms | 2006-07-28 | |
local.embargo.lift | 2006-07-28 | |
dc.contributor.committeeChair | Richard Alan Peters, II | |