Abstract
The path planning is a basic research question, where an Agent is going to look for an optimal path from the beginning to the terminal point. The earliest research problem was obstacle avoidance, that is, the Agent could not collide with obstacles or fall into traps in the process of path optimization. With rapid development of the AI (artificial intelligence) technology, the path planning has become an important application field to test intelligent learning algorithms, where reinforcement learning as an active learning method has the obvious advantage in path planning compared with traditional supervised learning and unsupervised learning. As is known to all, Q-Learning is one of the most successful reinforcement learning algorithms, and it surely can help solve the path planning. Aiming at the problems of slower convergence of the existing Q-Learning algorithm, this paper introduces dynamic search factor technology and puts forward a novel ɛ-Q-Learning algorithm. Experiments show that compared with the existing Q Learning algorithm, the ɛ-Q-Learning algorithm can not only present a better optimal solution, but also significantly reduce the number of iterations to quickly complete the optimal path generation.
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 subscriptionsReferences
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT press, Cambridge (1998)
Gao, Y., Chen, S., Lu, X.: Review of reinforcement learning. J. Autom. 30(1), 86–100 (2004)
Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3–4), 279–292 (1992)
Qiao, J., Hou, Z., Yan, X.: Application of reinforcement learning based on neural network in obstacle avoidance. J. Tsinghua Univ. Nat. Sci. Ed. 48(S2), 1747–1750 (2008)
Fakoor, M., Kosari, A., Jafarzadeh, M.: Humanoid robot path planning with fuzzy Markov decision processes. J. Appl. Res. Technol. 14(5), 300–310 (2016)
Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. 4, 237–285 (1996)
He, D., Sun, S.: An online self-learning fuzzy navigation method for mobile robots. J. Xi’an Univ. Technol. 27(4), 325–329 (2007)
Hao, C., Fang, Z., Li, P.: Three-dimensional track planning algorithm of UAV based on Q learning. J. Shanghai Jiaotong Univ. 46(12), 1931–1935 (2012)
Liu, Z., Li, H., Liu, Q.: Reinforcement learning algorithm research. Comput. Eng. Des. 29(22), 5805–5809 (2008)
Roozegar, M., et al.: XCS-based reinforcement learning algorithm for motion planning of a spherical mobile robot. Appl. Intell. 45, 736–746 (2016)
Chen, C.L.: Autonomous learning and navigation control of mobile robot based on reinforcement learning. University of Science and Technology of China (2006)
Castronovo, M., Maes, F., Fonteneau, R., et al.: Learning exploration/exploitation strategies for single trajectory reinforcement learning. In: European Workshop on Reinforcement Learning, pp. 1–10 (2013)
Acknowledgment
This work is supported by the National Natural Science Foundation of China (61773415).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Gu, S. (2020). An Algorithm for Path Planning Based on Improved Q-Learning. In: Pan, JS., Lin, JW., Liang, Y., Chu, SC. (eds) Genetic and Evolutionary Computing. ICGEC 2019. Advances in Intelligent Systems and Computing, vol 1107. Springer, Singapore. https://doi.org/10.1007/978-981-15-3308-2_3
Download citation
DOI: https://doi.org/10.1007/978-981-15-3308-2_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3307-5
Online ISBN: 978-981-15-3308-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)