Abstract
In this paper we present an application of Reinforcement Learning (RL) methods in the field of robot control. The main objective is to analyze the behavior of batch RL algorithms when applied to a mobile robot of the kind called Mobile Wheeled Pendulum (MWP). In this paper we focus on the common problem in classical control theory of following a reference state (e.g., position set point) and try to solve it by RL. In this case, the state space of the robot has one more dimension, in order to represent the desired variable state, while the cost function is evaluated considering the difference between the state and the reference. Within this framework some interesting aspects arise, like the ability of the RL algorithm to generalize to reference points never considered during the training phase. The performance of the learning method has been empirically analyzed and, when possible, compared to a classic control algorithm, namely linear quadratic optimal control (LQR).
Chapter PDF
References
Baird, L.C.: Residual algorithms: Reinforcement learning with function approximation. In: Proceedings of the 12th Intl. Conf. on Machine Learning, pp. 30-37 (1995)
Ernst, D., Geurts, P., Wehenkel, L.: Tree-based batch mode reinforcement learning. Journal of Machine Learning Research 6, 503-556 (2005)
Gordon, G.J.: Approximate solutions to markov decision processes. Ph.D. thesis, Carnegie Mellon University (1999)
Landau, L., Lifshitz, E.M.: Mechanics, Course of Theoretical Physics, Volume 1. Pergamon Pres (1976)
Ogata, K.: Modern Control Engineering (4th ed.). Prentice Hall PTR, Upper Saddle River, NJ, USA (2001)
Ormoneit, D., Sen, S.: Kernel-based reinforcement learning. Machine Learning 49(2-3), 161-178 (2002)
Press, W.H., Flannery, B.P., Teukolsky, S.A., Vetterling, W.T.: Numerical Recipes: The Art of Scientific Computing. Cambridge Univ. Press, New York, 1989. (1989)
Reddy, J.: Energy Principles and Variational Methods in Applied Mechanics (2nd ed.). John Wiley and Sons, Hoboken, NJ, USA (2002)
Riedmiller, M.: Neural fitted q iteration - first experiences with a data efficient neural reinforcement learning method. In: Proceedings of European Conference on Machine Learning, pp. 317-328 (2005)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge, MA (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 International Federation for Information Processing
About this paper
Cite this paper
Bonarini, A., Caccia, C., Lazaric, A., Restelli, M. (2008). Batch Reinforcement Learning for Controlling a Mobile Wheeled Pendulum Robot. In: Bramer, M. (eds) Artificial Intelligence in Theory and Practice II. IFIP AI 2008. IFIP – The International Federation for Information Processing, vol 276. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-09695-7_15
Download citation
DOI: https://doi.org/10.1007/978-0-387-09695-7_15
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-09694-0
Online ISBN: 978-0-387-09695-7
eBook Packages: Computer ScienceComputer Science (R0)