Abstract
In this paper, we point out problems in concurrent Q-learning (CQL), which is one of the adaptation techniques to dynamic environment in reinforcement learning and propose the modification of the relaxation procedure in CQL. We apply the proposed algorithm to the problem of maze in reinforcement learning and validate what kind of behavior the original CQL and the proposed algorithm show for the changes of environment such as the change of goals and the emergence of obstacles.
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
Sutton, R.S., Barto, A.G.: Reinforcement learning - an introduction. MIT Press (1998)
Morris, R.G.M.: Spatial localization does not require the presence of local cues. Learning and Motivation 12, 239–260 (1981)
Foster, D.J., Morris, R.G.M., Dayan, P.: A model of hippocampally dependent navigation using the temporal difference learning rule. Hippocampus 10, 1–16 (2000)
Kaelbling, L.P.: Learning to achieve goals. In: Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence (1993)
Ollington, R.B., Vamplew, P.W.: Concurrent Q-learning: reinforcement learning for dynamic goals and environments. International Journal of Intelligent Systems 20, 1037–1052 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Murakami, K., Ozeki, T. (2013). Improvement of the Relaxation Procedure in Concurrent Q-Learning. In: Lee, M., Hirose, A., Hou, ZG., Kil, R.M. (eds) Neural Information Processing. ICONIP 2013. Lecture Notes in Computer Science, vol 8227. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-42042-9_11
Download citation
DOI: https://doi.org/10.1007/978-3-642-42042-9_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-42041-2
Online ISBN: 978-3-642-42042-9
eBook Packages: Computer ScienceComputer Science (R0)