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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews 38(2), 156–172 (2008)
Duro, R.J., Graña, M., de Lope, J.: On the potential contributions of hybrid intelligent approaches to multicomponen robotic system development. Information Sciences 180(14), 2635–2648 (2010)
Echegoyen, Z., Villaverde, I., Moreno, R., Graña, M., d’Anjou, A.: Linked multi-component mobile robots: modeling, simulation and control. Robotics and Autonomous Systems 58(12), 1292–1305 (2010)
Fernandez-Gauna, B., Lopez-Guede, J.M., Zulueta, E., Graña, M.: Learning hose transport control with Q-learning. Neural Network World 20(7), 913–923 (2010)
Fernandez-Gauna, B., Lopez-Guede, J.M., Zulueta, E.: Linked multicomponent robotic systems: Basic assessment of linking element dynamical effect. In: Graña Romay, M., Corchado, E., Garcia Sebastian, M.T. (eds.) HAIS 2010. LNCS, vol. 6076, pp. 73–79. Springer, Heidelberg (2010)
Fernandez-Gauna, B., Lopez-Guede, J.M., Zulueta, E., Echegoyen, Z., Graña, M.: Basic results and experiments on robotic multi-agent system for hose deployment and transportation. International Journal of Artificial Intelligence 6(S11), 183–202 (2011)
Ferrández, J.M., de la Paz, F., de Lope, J.: Intelligent robotics and neuroscience. Neurocomputing 58(12), 1221–1222 (2010)
Graña, M., Torrealdea, F.J.: Hierarchically structured systems. European Journal of Operational Research 25, 20–26 (1986)
Maravall, D., de Lope, J., Martin, J.A.: Hybridizing evolutionary computation and reinforcement learning for the design of almost universal controllers for autonomous robots. Neurocomputing 72(4-6), 887–894 (2009)
Panait, L., Luke, S.: Cooperative multi-agent learning: The state of the art. Autonomous Agents and Multi-Agent Systems 11(3), 387–434 (2005)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Whitehead, S., Karlsson, J., Tenenberg, J.: Learning multiple goal behavior via task decomposition and dynamic policy merging. In: Robot Learning, pp. 45–78. Kluwer Academic Publishers, Dordrecht (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fernandez-Gauna, B., Lopez-Guede, J.M., Graña, M. (2011). Towards Concurrent Q-Learning on Linked Multi-Component Robotic Systems. In: Corchado, E., Kurzyński, M., Woźniak, M. (eds) Hybrid Artificial Intelligent Systems. HAIS 2011. Lecture Notes in Computer Science(), vol 6679. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-21222-2_56
Download citation
DOI: https://doi.org/10.1007/978-3-642-21222-2_56
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-21221-5
Online ISBN: 978-3-642-21222-2
eBook Packages: Computer ScienceComputer Science (R0)