Abstract
This paper presented a novel approach accuracy-based learning classifier system with gradient descent (XCS-GD) to research on swarm robots reinforcement learning convergence. XCS-GD combines covering operator and genetic algorithm. XCS-GD is responsible for adjusting precision and reducing search space according to some reward obtained from the environment, XCS-GD’s innovation discovery component is responsible for discovering new better reinforcement learning rules. The experiment and simulation showed that XCS-GD approach can achieve convergence very quickly in swarm robots reinforcement learning.
Similar content being viewed by others
References
Shao J, Yang J, Wan M, Huang C (2010) Research on convergence of multi-robot path planning based on learning classifier system. J Comput Res Dev 47(5):948–955
Lan T, Liu S (2007) Research on multi-robot robot system inspired by biological swarm intelligence. Robot 29(3):298–304
Shao J, Yang J (2009) Research on convergence of robot path planning based on LCS. In: Proceedings of Chinese conference on pattern recognition, Oct 22–24, Nanjing, China, pp 271–276
Dixon PW, Corne DW, Oates MJ (2002) A preliminary investigation of modified XCS as a generic data mining tool. Adv Learn Classif Syst 2321:133–150
Gemeinder M, Gerke M (2003) GA-based path planning for mobile robot systems employing an active search algorithm. Appl Soft Comput 3:149–158
Baneamoon SM, Abdul Salam R, Talib AZH (2007) Learning process enhancement for robot behaviors. Int J Intell Technol 2(3):172–177
Bull L, Studley M, Bagnall A, Whittley I (2007) Learning classifier system ensembles with rule-sharing. IEEE Trans Evol Comput 11(4):496–502
Baneamoon SM, Salam RA (2008) Applying steady state in genetic algorithm for robot behaviors. In: 2008 International conference on electronic design. IEEE, Piscataway, NJ, pp 930–934
Bull L (2003) A simple accuracy-based learning classifier system. University of the West of England, Bristol
Wang Y, Huber M, Papudesi VN, Cook DJ (2003) User-guided reinforcement learning of robot assistive tasks for an intelligent environment. Proc IEEE/RJS Int Conf Intell Robots Syst 1:424–429
Bull L, Kovacs T (2005) Foundations of learning classifier systems: an introduction. Found Learn Classif Syst 183:1–17
Musilek P, Li S, Wyard-Scot L (2005) Enhanced learning classifier system for robot navigation. In: IROS 2005, IEEE/RSJ International conference on intelligent robots and systems, Alberta, Canada, 2–6 Aug 2005, pp 3390–3395
Bull L, Sha’Aban J, Tomlinson A, Addison JD, Heydecker BG (2004) Towards distributed adaptive control for road traffic junction signals using learning classifier systems. In: Bull L (ed) Applications of learning classifier systems. Springer, Berlin, pp 276–299
Bay SJ (1995) Learning classifier systems for single and multiple mobile robots in unstructured environments. Mobile Robots X, Philadelphia, PA, pp 88–99
Acknowledgments
The authors would like to thank the anonymous reviewers and the editor for their helpful comments and suggestions. This work is partially supported by 2013 Henan College “professional comprehensive reform pilot” project and 2012 Education Department of Henan Science and Technology Research Key Project.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Shao, J., Lin, H. & Zhang, K. Swarm robots reinforcement learning convergence accuracy-based learning classifier systems with gradient descent (XCS-GD). Neural Comput & Applic 25, 263–268 (2014). https://doi.org/10.1007/s00521-013-1503-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-013-1503-y