Abstract
In view of the deployment environment of the adaptive system is complex, dynamic, unpredictable, focusing on the construction of dynamic, uncertain environment adaptive system, and this paper combines the reinforcement learning technology and software agent technology to propose an adaptive mechanism based on shared learning in multiple agent system. Based on this, framework for constructing adaptive systems and shared learning algorithm of agent are given. Finally, by conducting a comparative experiment and result analysis to verify the feasibility of the theory put forward by this article.
Chapter PDF
Similar content being viewed by others
References
Szepesvári, C.: Algorithms for reinforcement learning. Synthesis Lectures on Artificial Intelligence and Machine Learning 4(1), 1–103 (2010)
Meignan, D., Koukam, A., Créput, J.C.: Coalition-based metaheuristic: a self-adaptive metaheuristic using reinforcement learning and mimetism. Journal of Heuristics 16(6), 859–879 (2010)
Salehie, M., Tahvildari, L.: Self-Adaptive Software: Landscape and Research Challenges. ACM Transactions on Autonomous and Adaptive Systems 4(2), 1–42 (2009)
Kabysh, A., Golovko, V., Lipnickas, A.: Influence Learning for Multi-Agent Systems Based on Reinforcement Learning. International Journal of Computing 11(1), 39–44 (2012)
Smarsly, K., Law, K.H., Hartmann, D.: Multiagent-based collaborative framework for a self-managing structural health monitoring system. Journal of Computing in Civil Engineering 26(1), 76–89 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 IFIP International Federation for Information Processing
About this paper
Cite this paper
Li, Q., Chu, H., Diao, L., Wang, L. (2014). Adaptive Mechanism Based on Shared Learning in Multi-agent System. In: Shi, Z., Wu, Z., Leake, D., Sattler, U. (eds) Intelligent Information Processing VII. IIP 2014. IFIP Advances in Information and Communication Technology, vol 432. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-662-44980-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-662-44980-6_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-662-44979-0
Online ISBN: 978-3-662-44980-6
eBook Packages: Computer ScienceComputer Science (R0)