Abstract
Reinforcement learning is a learning framework that is especially suited for obstacle avoidance and navigation of autonomous mobile robots, because supervised signals, hardly available in the real world, can be dispensed with. We have to determine, however, the values of parameters in reinforcement learning without prior information. In the present paper, we propose to use a genetic algorithm with inheritance for their optimization. We succeed in decreasing the average number of actions needed to reach a given goal by about 10-40% compared with reinforcement learning with non-optimal parameters, and in obtaining a nearly shortest path.
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
Sutton, R.S., Barto, A.G.: Reinforcement Learning. MIT Press, Cambridge (1998)
Unsal, C., Kachroo, P., Bay, J.S.: Multiple Stochastic Learning Automata for Vehicle Path Control in an Automated Highway System. In: Proceedings of the 1999 IEEE Trans. Systems, Man, and Cybernetics, Part A: Systems and Humans, vol. 29, pp. 120–128 (1999)
Svinin, M.M., Yamada, K., Ueda, K.: Emergent synthesis of motion patterns for locomotion robots. Artificial Intelligence in Engineering 15(4), 353–363 (2001)
Balkenius, C., Moren, J.: Dynamics of a classical conditioning model. Autonomous Robots 7, 41–56 (1999)
Pfeifer, R., Scheier, C.: Understanding Intelligence. MIT Press, Cambridge (1999)
Pettinger, J.E., Everson, R.M.: Controlling Genetic Algorithms with Reinforcement Learning. Department of Computer Science, School of Engneering and Computer Science, University of Exeter. EX4 4QF, UK (2003)
Calderoni, S., Marcenac, P.: MUTANT: a MultiAgent Toolkit for Artificial Life Simulation. In: The Proceedings of TOOLS-26 1998, Santa Barbara, California, August 3-7. IEEE, Los Alamitos (1998)
Lee, M.R., Rhee, H.: The effect of evolution in artificial life learning behavior. Journal of intelligent and robotic systems 30, 399–414 (2001)
Abu-Zitar, R., Nuseirat, A.M.A.: A theoretical approach of an intelligent robot gripper to grasp polygon shaped objects. Journal of intelligent and robotic systems 31, 397–422 (2001)
Lin, C.T., Jou, C.P.: GA-based fuzzy reinforcement learning for control of a magnetic bearing systems. Proceedings of the 2002 IEEE Trans. Systems, Man, and Cybernetics, Part B: Cybernetics 30, 276–289 (2000)
Stafylopatis, A., Blekas, K.: Autonomous vehicle navigation using evolutionary reinforcement learning. European Journal of Operational Research 108, 306–318 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kamei, K., Ishikawa, M. (2004). A Genetic Approach to Optimizing the Values of Parameters in Reinforcement Learning for Navigation of a Mobile Robot. In: Pal, N.R., Kasabov, N., Mudi, R.K., Pal, S., Parui, S.K. (eds) Neural Information Processing. ICONIP 2004. Lecture Notes in Computer Science, vol 3316. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30499-9_178
Download citation
DOI: https://doi.org/10.1007/978-3-540-30499-9_178
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23931-4
Online ISBN: 978-3-540-30499-9
eBook Packages: Springer Book Archive