Paper Info
Title
Towards concurrent Q-learning on linked multi-component robotic systems
Abstract
When conventional Q-Learning is applied to Multi-Component Robotic Systems (MCRS), increasing the number of components produces an exponential growth of state storage requirements. Modular approaches make the state size growth polynomial on the number of components, making more manageable its representation and manipulation. In this article, we give the first steps towards a modular Q-learning approach to learn the distributed control of a Linked MCRS, which is a specific type of MCRSs in which the individual robots are linked by a passive element. We have chosen a paradigmatic application of this kind of systems: a set of robots carrying the tip of a hose from some initial position to a desired goal. The hose dynamics is simplified to be a distance constraint on the robots positions.
Year
DOI
Venue
2011
10.1007/978-3-642-21222-2_56
HAIS (2)
Keywords
Field
DocType
towards concurrent q-learning,multi-component robotic systems,exponential growth,hose dynamic,conventional q-learning,state storage requirement,state size growth polynomial,robots position,linked mcrs,multi-component robotic system,modular approach,modular q-learning approach
Robotic systems,Polynomial,Computer science,Q-learning,Artificial intelligence,Modular design,Robot,Machine learning,Exponential growth
Conference
Volume
ISSN
Citations 
6679
0302-9743
4
PageRank 
References 
Authors
0.52
7
3
Name
Order
Citations
PageRank
Borja Fernandez-Gauna1494.89
Jose Manuel Lopez-Guede2223.25
Manuel Graña31367156.11