Abstract
To acquire adaptive behaviors of multiple agents in the unknown environment, several neuro-fuzzy reinforcement learning systems (NFRLSs) have been proposed Kuremoto et al. Meanwhile, to manage the balance between exploration and exploitation in fuzzy reinforcement learning (FRL), an adaptive learning rate (ALR), which adjusting learning rate by considering “fuzzy visit value” of the current state, was proposed by Derhami et al. recently. In this paper, we intend to show how the ALR accelerates some NFRLSs which are reinforcement learning systems with a self-organizing fuzzy neural network (SOFNN) and different learning methods including actor-critic learning (ACL), and Sarsa learning (SL). Simulation results of goal-exploration problems showed the powerful effect of the ALR comparing with the conventional empirical fixed learning rates.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Kaelbling, L.P., Littman, M.L.: Reinforcement Learning: A Survey. J. Artificial Intelligence Research 4, 237–285 (1996)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)
Samejima, K., Omori, T.: Adaptive Internal State Space Construction Method for Reinforcement Learning of a Real-World Agent. Neural Networks 12, 1143–1155 (1999)
Wang, X.S., Cheng, Y.H., Yi, J.Q.: A fuzzy Actor–Critic Reinforcement Learning Network. Information Sciences 177, 3764–3781 (2007)
Kuremoto, T., Obayashi, M., Kobayashi, K.: Adaptive Swarm Behavior Acquisition by a Neuro-Fuzzy System and Reinforcement Learning Algorithm. Intern. J. of Intelligent Computing and Cybernetics 2(4), 724–744 (2009)
Kuremoto, T., Yamano, Y., Obayashi, M., Kobayashi, K.: An Improved Internal Model for Swarm Formation and Adaptive Swarm Behavior Acquisition. J. of Circuits, Systems, and Computers 18(8), 1517–1531 (2009)
Kuremoto, T., Yamano, Y., Feng, L.-B., Kobayashi, K., Obayashi, M.: A Fuzzy Neural Network with Reinforcement Learning Algorithm for Swarm Learning. In: Zhang, Y. (ed.) Future Computing, Communication, Control and Management. LNEE, vol. 144, pp. 101–108. Springer, Heidelberg (2011)
Derhami, V., Majd, V.J., Ahmadabadi, M.N.: Exploration and Exploitation Balance Management in Fuzzy Reinforcement Learning. Fuzzy Sets and Systems 161(4), 578–595 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Kuremoto, T., Obayashi, M., Kobayashi, K., Mabu, S. (2014). How an Adaptive Learning Rate Benefits Neuro-Fuzzy Reinforcement Learning Systems. In: Tan, Y., Shi, Y., Coello, C.A.C. (eds) Advances in Swarm Intelligence. ICSI 2014. Lecture Notes in Computer Science, vol 8794. Springer, Cham. https://doi.org/10.1007/978-3-319-11857-4_37
Download citation
DOI: https://doi.org/10.1007/978-3-319-11857-4_37
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11856-7
Online ISBN: 978-3-319-11857-4
eBook Packages: Computer ScienceComputer Science (R0)