| Type of Document |
Master's Thesis |
| Author |
Conn, Karla Gail
|
| Author's Email Address |
karla.g.conn@vanderbilt.edu |
| URN |
etd-07272005-114235 |
| Title |
SUPERVISED-REINFORCEMENT LEARNING FOR A MOBILE ROBOT IN A REAL-WORLD ENVIRONMENT |
| Degree |
Master of Science |
| Department |
Electrical Engineering |
| Advisory Committee |
| Advisor Name |
Title |
| Richard Alan Peters, II |
Committee Chair |
| Douglas Fisher |
Committee Member |
|
| Keywords |
- intelligent machine
- mobile robot
- reinforcement learning
|
| Date of Defense |
2005-07-18 |
| Availability |
unrestricted |
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.
|
| Files |
| Filename |
Size |
Approximate Download Time
(Hours:Minutes:Seconds)
|
| 28.8 Modem |
56K Modem |
ISDN (64 Kb) |
ISDN (128 Kb) |
Higher-speed Access |
| |
ConnKarlaG_MSEEThesis.pdf |
3.76 Mb |
00:17:23 |
00:08:56 |
00:07:49 |
00:03:54 |
00:00:20 |
|
