Adaptive Learning for Efficient Emergence of Social Norms in Networked Multiagent Systems

详细信息    查看全文

• 关键词：Norm emergence ; Learning ; Multiagent systems
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：9810
• 期：1
• 页码：805-818
• 全文大小：799 KB
• 参考文献：1.Shoham, Y., Tennenholtz, M.: On the emergence of social conventions: modeling, analysis, and simulations. Artif. Intel. 94(1–2), 139–166 (1997)CrossRef MATH
  2.Hao, J., Sun, J., Huang, D., Cai, Y., Yu, C.: Heuristic collective learning for efficient and robust emergence of social norms. In: Proceeedings of 14th AAMAS, pp. 1647–1648 (2015)
  3.Hasan, M., Raja, A., Bazzan, A.: Fast convention formation in dynamic networks using topological knowledge. In: Proceedings of 29th AAAI, pp. 2067–2073. IEEE (2015)
  4.Brooks, L., Iba, W., Sen, S.: Modeling the emergence and convergence of norms. In: Proceedings of 22nd IJCAI, pp. 97–102 (2011)
  5.Savarimuthu, B.: Norm learning in multi-agent societies (2011)
  6.Sen, S., Airiau, S.: Emergence of norms through social learning. In: Proceedings of 20th IJCAI, pp. 1507–1512 (2007)
  7.Mukherjee, P., Sen, S., Airiau, S.: Norm emergence under constrained interactions in diverse societies. In: Proceedings of 7th AAMAS, pp. 779–786 (2008)
  8.Villatoro, D., Sen, S., Sabater-Mir, J.: Topology and memory effect on convention emergence. In: Proceedings of WI-IAT 2009, pp. 233–240 (2009)
  9.Yu, C., Lv, H., Ren, F., Bao, H., Hao, J.: Hierarchical learning for emergence of social norms in networked multiagent systems. In: Proceedings of AI 2015, pp. 630–643 (2015)
  10.Villatoro, D., Sabater-Mir, J., Sen, S.: Social instruments for robust convention emergence. In: Proceedings of 22nd IJCAI, pp. 420–425 (2011)
  11.Yu, C., Zhang, M., Ren, F., Luo, X.: Emergence of social norms through collective learning in networked agent societies. In: Proceedings of AAMAS, pp. 475–482 (2013)
  12.Yu, C., Zhang, M., Ren, F.: Collective learning for the emergence of social norms in networked multiagent systems. IEEE Trans. Cybern. 44(12), 2342–2355 (2014)CrossRef
  13.Shibusawa, R., Sugawara, T.: Norm emergence via influential weight propagation in complex networks. In: Proceedings of ENIC, pp. 30–37. IEEE (2014)
  14.Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. The MIT Press, Cambridge (1998)
  15.Szabo, G., Fáth, G.: Evolutionary games on graphs. Phys. Rep. 446(4–6), 97–216 (2007)MathSciNet CrossRef
  16.Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artif. Intell. 136, 215–250 (2002)MathSciNet CrossRef MATH
  17.Young, H.P.: The economics of convention. J. Econ. Pers. 10(2), 105–122 (1996)CrossRef
  18.Mihaylov, M., Tuyls, K., Now, A.: A decentralized approach for convention emergence in multi-agent systems. Auton. Agent. Multi-Agent Syst. 15(2), 1–30 (2013)
  19.Barabási, A.L., Albert, R.: Statistical mechanics of complex networks. Rev. Modern Phys. 74, 47–97 (2002)MathSciNet CrossRef MATH
  20.Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279–292 (1992)MATH
  21.Airiau, S., Sen, S., Villatoro, D.: Emergence of conventions through social learning. Auton. Agent. Multi-Agent Syst. 28(5), 779–804 (2014)CrossRef
  22.Watts, D.J., Strogatz, S.H.: Collective dynamics of small-world networks. Nature 393, 440–442 (1998)CrossRef
  23.Delgado, J.: Emergence of social conventions in complex networks. Artif. Intell. 141(1), 171–185 (2002)MathSciNet CrossRef
  
• 作者单位：Chao Yu (15)
  Hongtao Lv (15)
  Sandip Sen (16)
  Fenghui Ren (17)
  Guozhen Tan (15)
  
  15. School of Computer Science and Technology, Dalian University of Technology, Dalian, 116024, China
  16. Department of Mathematical and Computer Sciences, University of Tulsa, Tulsa, OK, 74104, USA
  17. School of Computer Science and Software Engineering, University of Wollongong, Wollongong, 2500, Australia
  
• 丛书名：PRICAI 2016: Trends in Artificial Intelligence
• ISBN：978-3-319-42911-3
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：9810

文摘

This paper investigates how norm emergence can be facilitated by agents’ adaptive learning behaviors in networked multiagent systems. A general learning framework is proposed, in which agents can dynamically adapt their learning behaviors through social learning of their individual learning experience. Extensive verification of the proposed framework is conducted in a variety of situations, using comprehensive evaluation criteria of efficiency, effectiveness and efficacy. Experimental results show that the adaptive learning framework is robust and efficient for evolving stable norms among agents.