Abstract
We propose an integrated technique of genetic programming (GP) and reinforcement learning (RL) that allows a real robot to execute real-time learning. Our technique does not need a precise simulator because learning is done with a real robot. Moreover, our technique makes it possible to learn optimal actions in real robots. We show the result of an experiment with a real robot AIBO and represents the result which proves proposed technique performs better than traditional Q-learning method.
This is a preview of subscription content, log in via an institution to check access.
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
John R. Koza: Genetic Programming, On the Programming of Computers by means of Natural Selection. MIT Press (1992)
Richard S. Sutton and Andrew G. Barto: Reinforcement Learning: An introduction. MIT Press in Cambridge, MA (1998)
Hajime Kimura, Toru Yamashita and Shigenobu Kobayashi: Reinforcement Learning of Walking Behavior for a Four-Legged Robot. In: 40th IEEE Conference on Decision and Control. (2001)
Minoru Asada, Shoichi Noda, Sukoya Tawaratsumida and Koh Hosoda: Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning. Machine Learning 23 (1996) 279–303
Yasutake Takahashi, Minoru Asada, Shoichi Noda and Koh Hosoda: Sensor Space Segmentation for Mobile Robot Learning. In: Proceedings of ICMAS’96 Workshop on Learning, Interaction and Organizations in Multiagent Environment. (1996)
OPEN-R Programming Special Interest Group: Introduction to OPEN-R programming (in Japanese). Impress corporation (2002)
Hitoshi Iba: Multi-Agent Reinforcement Learning with Genetic Programming. In: Proc. of the Third Annual Genetic Programming Conference. (1998)
Keith L. Downing: Adaptive genetic programs via reinforcement learning. In: Proc. of the Third Annual Genetic Programming Conference. (1998)
Moriarty, D.E., Schultz, A.C., Grefenstette, J.J.: Evolutionary algorithms for reinforcement learning. Journal of Artificial Intelligence Research 11 (1999) 199–229
Dorigo, M., Colombetti, M.: Robot Shaping: An Experiment in Behavior Engineering. MIT Press (1998)
L.P. Kaelbling: Hierarchical Learning in Stochastic Domains: preliminary Results. In: Proc. 10th Int. Conf. on Machine Learning. (1993) 167–173
T.G. Dietterich: Hierarchical reinforcement learning with the MAXQ value function decomposition. Journal of Artificial Intelligence Research 13:227 303 (2000)
Schultz, A.C., Ramsey, C.L., Grefenstette, J.J.: Simulation-assisted learning by competition: Effects of noise differences between training model and target environment. In: Proc. of Seventh International Conference on Machine Learning, San Mateo, Morgan Kaufmann (1990) 211–215
Kohsuke Yanai and Hitoshi Iba: Multi-agent Robot Learning by Means of Genetic Programming: Solving an Escape Problem. In Liu, Y., et al., eds.: Evolvable Systems: From Biology to Hardware. Proceedings of the 4th International Conference on Evolvable Systems, ICES’2001, Tokyo, October 3–5, 2001, Springer-Verlag, Berlin, Heidelberg (2001) 192–203
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kamio, S., Mitsuhashi, H., Iba, H. (2003). Integration of Genetic Programming and Reinforcement Learning for Real Robots. In: Cantú-Paz, E., et al. Genetic and Evolutionary Computation — GECCO 2003. GECCO 2003. Lecture Notes in Computer Science, vol 2723. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45105-6_59
Download citation
DOI: https://doi.org/10.1007/3-540-45105-6_59
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40602-0
Online ISBN: 978-3-540-45105-1
eBook Packages: Springer Book Archive