DocumentCode
399708
Title
Reinforcement learning on an omnidirectional mobile robot
Author
Hafner, Roland ; Riedmiller, Martin
Author_Institution
Informatik Lehrstuhl 1, Dortmund Univ., Germany
Volume
1
fYear
2003
fDate
27-31 Oct. 2003
Firstpage
418
Abstract
With this paper we describe a well suited, scalable problem for reinforcement learning approaches in the field of mobile robots. We show a suitable representation of the problem for a reinforcement approach and present our results with a model based standard algorithm. Two different approximators for the value function are used, a grid based approximator and a neural network based approximator.
Keywords
approximation theory; learning (artificial intelligence); mobile robots; neural nets; grid based approximator; neural network based approximator; omnidirectional mobile robot; reinforcement learning; value function; Gears; Learning systems; Machine learning; Mobile robots; Neural networks; Robot kinematics; Robotic assembly; Testing; Wheels;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Robots and Systems, 2003. (IROS 2003). Proceedings. 2003 IEEE/RSJ International Conference on
Print_ISBN
0-7803-7860-1
Type
conf
DOI
10.1109/IROS.2003.1250665
Filename
1250665
Link To Document