Abstract
In this article we present an approach that enables robots to learn how to act and react robustly in continuous and noisy environments while not loosing track of the overall feasibility, i.e. minimising the execution time in order to keep up continuous learning. We do so by combining reinforcement learning mechanisms with techniques belonging to the field of multivariate statistics on three different levels of abstraction: the motivation layer and the two simultaneously learning strategy and skill layers. The motivation layer allows for modelling occasionally contradicting goals in terms of drives in a very intuitive fashion. A drive represents one single goal, that a robot wants to be satisfied, like charging its battery, when it is nearly exhausted, or transporting an object to a target position. The strategy layer encapsulates the main reinforcement learning algorithm based on an abstracted and dynamically adjusted Markovian state space. By means of state abstraction, we minimise the overall state space size in order to ensure feasibility of the learning process in a dynamically changing environment. The skill layer finally realises a generalised learning method for learning reactive low-level behaviours, that enable a robot to interact with the environment.
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
Alpaydin, E.: Introduction to Machine Learning. MIT Press, Cambridge (2004)
Cover, T., Hart, P.: Nearest neighbor pattern classification. IEEE Trans. Inf. Theory 13(1), 21–27 (1967)
Herbrechtsmeier, S., Witkowski, U., Rückert, U.: BeBot: a modular mobile miniature robot platform supporting hardware reconfiguration and multi-standard communication. In: Progress in Robotics. Communications in Computer and Information Science, vol. 44, pp. 346–356. Springer, Berlin (2009)
Jolliffe, I.T.: Principal Component Analysis. Springer, Berlin (2002)
Kochenderfer, M.J.: Adaptive modelling and planning for learning intelligent behaviour. PhD thesis, School of Informatics, University of Edinburgh (2006)
Konda, V.R., Tsitsiklis, J.N.: On actor-critic algorithms. SIAM J. Control Optim. 42(4), 1143–1166 (2003)
Lazaric, A., Restelli, M., Bonarini, A.: Reinforcement learning in continuous action spaces through sequential Monte Carlo methods. In: Advances in Neural Information Processing Systems, vol. 20, pp. 833–840. MIT Press, Cambridge (2008)
Moore, A., Atkeson, C.: Prioritized sweeping: Reinforcement learning with less data and less time. Mach. Learn. 13(1), 103–130 (1993)
Nilsson, N.J.: Artificial Intelligence: A New Synthesis. Morgan Kaufmann, San Mateo (1998)
Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming. Wiley-Interscience, New York (1994)
Richert, W., Lüke, O., Nordmeyer, B., Kleinjohann, B.: Increasing the autonomy of mobile robots by on-line learning simultaneously at different levels of abstraction. In: Proceedings of the Fourth International Conference on Autonomic and Autonomous Systems, pp. 154–159. IEEE Computer Society, Los Alamitos (2008)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
van Hasselt, H., Wiering, M.A.: Reinforcement learning in continuous action spaces. In: IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning (ADPRL), pp. 272–279 (2007)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer Basel AG
About this chapter
Cite this chapter
Jungmann, A., Kleinjohann, B., Richert, W. (2011). A Fast Hierarchical Learning Approach for Autonomous Robots. In: Müller-Schloer, C., Schmeck, H., Ungerer, T. (eds) Organic Computing — A Paradigm Shift for Complex Systems. Autonomic Systems, vol 1. Springer, Basel. https://doi.org/10.1007/978-3-0348-0130-0_36
Download citation
DOI: https://doi.org/10.1007/978-3-0348-0130-0_36
Publisher Name: Springer, Basel
Print ISBN: 978-3-0348-0129-4
Online ISBN: 978-3-0348-0130-0
eBook Packages: Computer ScienceComputer Science (R0)