Abstract
Reinforcement learning (RL) is suitable for navigation of a mobile robot. We overcame some difficulties of RL which are large computational cost and determination of parameter values for RL with the help of a genetic algorithm (GA) and method of parameter prediction based on results of GA and complexity measure. As a result of these proposals, we succeeded in navigating the real robot practically. In our previous studies, we just one kind of mobile robot, which has three wheels. Our RL method can decrease the computational cost for learning of navigation and development of mobile robots, provided the skill obtained by RL for one mobile robot can be transferred to other mobile robots.
To verify the generalization capability of RL in navigation of a mobile robot, the present paper proposes to transfer the skill obtained by RL to a different kind of a mobile robot. We carried out the experiment and we succeeded in transferring the skill obtained by RL to a different mobile robot.
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
Sutton, R.S., Barto, A.G.: Reinforcement Learning. MIT Press, Cambridge (1998)
Kamei, K., Ishikawa, M.: More Effective Reinforcement Learning by Introducing Sensory Information. In: International Joint Conference on Neural Networks, pp. 3185–3188 (2004)
Kamei, K., Ishikawa, M.: Improvement of performance of reinforcement learning by introducing sensory information and a GA with inheritance. In: International Conference on Neural Information Processing 2005, pp. 1148–1153 (2005)
Kamei, K., Ishikawa, M.: Reduction of computational cost in optimization of parameter values in reinforcement learning by a genetic algorithm. In: Brain inspired-IT 2005. International Congress Series, vol. 1291, pp. 185–188 (2005)
Kamei, K., Ishikawa, M.: Dependency of Parameter Values in Reinforcement Learning for Navigation of a Mobile Robot on the Environment. Neural Information Processing - Letters and Reviews 10(7-9), 219–226 (July - September)
Kamei, K., Ishikawa, M.: Prediction of the optimal parameter values in reinforcement learning as a function of the environment. Brain inspired-IT 2006 Edited book (to appear)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kamei, K., Ishikawa, M. (2010). Skill Transfer of a Mobile Robot Obtained by Reinforcement Learning to a Different Mobile Robot. In: Hanazawa, A., Miki, T., Horio, K. (eds) Brain-Inspired Information Technology. Studies in Computational Intelligence, vol 266. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04025-2_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-04025-2_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04024-5
Online ISBN: 978-3-642-04025-2
eBook Packages: EngineeringEngineering (R0)