Abstract
Purpose of this system is to adapt the bedridden people who cannot move their body easily, so the simple reinforcement signals are applied. The application is to control the behaviors of Khepera robot, which is a small mobile robot. For the simple reinforcement signals the on-off signals are employed when the operators as the training agent feels discomfort for the behaviors of the learning agent Khepera robot. We proposed the new reinforcement learning method called Interactive Q-learning and the heterogeneous multi agent system. Our multi agent system has three kinds of heterogeneous single agent: Learning agent, Training agent and Interface Agent. The system is hierarchic. There are also three hierarchies. It is impossible to iterate the many episodes and steps to converge the learning which is adopted in general reinforcement learning in simulation world. We show the results of experiments using the Khepera robot for 3 examinees, and discuss how to give the rewards according to each operator and the significance of heterogeneous multi agent system. We confirmed the effectiveness through the some experiments which are to control the behavior of Khepera robot in real world. The convergences of our learning system are quite quick. Furthermore the importance of the interface agent is indicated. The individual differences for the timing to give the penalties are happened even though all operators are young.
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
Watkins C.J.C.H. (1992). Q-Learning, Machine Learning 8 p279
Sutton, R.S. and A.G. Barto (1998). Reinforcement Learning An Introduction MIT
Lee, C and Xu, Y (1996) Online, Interactive Learning of Gestures for Human/Robot Interfaces, In Proceedings, IEEE international Conference on Robotics and Automation, vol.4, pp.2982–2987, MN
Yu, W, H. Yokoi and D. Nishikawa (1998). Adaptive Electromyograohic (EMG) Prosthetic and Control Using Reinforcement Learning, IAS-5JOS Press, pp.266–271
Ishiwaka, Y. H. Yokoi, and Kakazu, Y.(2000) Adaptive Learning Interface Used Physiological signals, Proceedings SMC 2000 Conference. Nashville, USA, pp. 32–38
Bradtke, S.J and Duff, M.O.(1994) Reinforcement Learning Method for Continuous Time Markov Decision Problems, Advances in Neural Information Processing Systems 7,pp.393–400
Parr, R. and Russell, S.(1995) Approximating Optimal Policies for Partially Observable Stochastic Domains, In Proceedings of the International Conference on Artificial Intelligence,pp. 1088–1094,Morgan Kaufmann
Nehmzow U. and McGonigle B.: “Achieving Rapid Adaptations in Robots by Means of External Tuition”, SAB, 1994
A. Cesta and D. D’Aloisi.:”Building Interfaces as Personal Agents”, Sigchi Bulletin, vol.3, 1996
Wiering M. and Schmidhuber J.: “HQ-Learning”, Adaptive Behavior vol 6. No.2, 1997
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Tokyo
About this paper
Cite this paper
Ishiwaka, Y., Yokoi, H., Kakazu, Y. (2002). Interactive Q-Learning on heterogeneous agents system for autonomous adaptive interface. In: Asama, H., Arai, T., Fukuda, T., Hasegawa, T. (eds) Distributed Autonomous Robotic Systems 5. Springer, Tokyo. https://doi.org/10.1007/978-4-431-65941-9_47
Download citation
DOI: https://doi.org/10.1007/978-4-431-65941-9_47
Publisher Name: Springer, Tokyo
Print ISBN: 978-4-431-65943-3
Online ISBN: 978-4-431-65941-9
eBook Packages: Springer Book Archive