Abstract
In multiagent systems, social norms serves as an important technique in regulating agents’ behaviors to ensure effective coordination among agents without a centralized controlling mechanism. In such a distributed environment, it is important to investigate how a desirable social norm can be synthesized in a bottom-up manner among agents through repeated local interactions and learning techniques. In this article, we propose two novel learning strategies under the collective learning framework, collective learning EV-l and collective learning EV-g, to efficiently facilitate the emergence of social norms. Extensive simulations results show that both learning strategies can support the emergence of desirable social norms more efficiently and be applicable in a wider range of multiagent interaction scenarios compared with previous work. The influence of different topologies is investigated, which shows that the performance of all strategies is robust across different network topologies. The influences of a number of key factors (neighborhood size, actions space, population size, fixed agents and isolated subpopulations) on norm emergence performance are investigated as well.
- T. Ågotnes and M. Wooldridge. 2010. Optimal social laws. In Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems, Volume 1. 667--674.Google Scholar
- A. Alexander, K. Lloyd, J. Pitt, and M. Sergot. 2005. A protocol for resource sharing in norm-governed ad hoc networks. In Declarative Agent Languages and Technologies II. 221--238.Google Scholar
- A. Alexander, S. Marek, and P. Jeremy. 2009. Specifying norm-governed computational societies. ACM Trans. Comput. Logic 10, 1 (2009), 1.Google Scholar
- A. L. Barabási, R. Albert, and H. Jeong. 2000. Scale-free characteristics of random networks: The topology of the world-wide web. Physica A 281, 1 (2000), 69--77.Google Scholar
Cross Ref
- C. K. Chan, J. Y. Hao, and H. F. Leung. 2015. Reciprocal social strategy in social repeated games. In Proceedings of International Conference on Tools with Artificial Intelligence. 966--973. Google Scholar
Digital Library
- N. Criado, E. Argente, A. Garrido, J. A. Gimeno, F. Igual, V. Botti, P. Noriega, and A. Giret. 2011. Norm enforceability in electronic institutions? In Coordination, Organizations, Institutions, and Norms in Agent Systems VI. 250--267. Google Scholar
Cross Ref
- H. Franks, N. Griffiths, and A. Jhumka. 2013. Manipulating convention emergence using influencer agents. Auton. Agents Multi-Agent Syst. 26, 3 (2013), 315--353. Google Scholar
Digital Library
- K. Genter, S. Zhang, and P. Stone. 2015. Determining placements of influencing agents in a flock. In Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems. 247--255.Google Scholar
- N. Griffiths. 2008. Tags and image scoring for robust cooperation. In Proceedings of the 7th International Joint Conference on Autonomous Agents and Multiagent Systems, Volume 2. 575--582.Google Scholar
- N. Griffiths and S. S. Anand. 2012. The impact of social placement of non-learning agents on convention emergence. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems. 1367--1368.Google Scholar
- N. Griffiths and M. Luck. 2010a. Changing neighbours: Improving tag-based cooperation. In Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems. 249--256.Google Scholar
- N. Griffiths and M. Luck. 2010b. Norm emergence in tag-based cooperation. In Proceedings of the 8th European Workshop on Multi-Agent Systems.Google Scholar
- J. Y. Hao and H. F. Leung. 2013. Achieving social optimality with influencer agents. In Complex Sciences. Springer, 140--151. Google Scholar
Cross Ref
- M. James, N. Griffiths, and M. Leeke. 2015. Convention emergence and influence in dynamic topologies. In Proceedings of International Conference on Autonomous Agents and Multiagent Systems. 1785--1786.Google Scholar
- S. Kapetanakis and D. Kudenko. 2002. Reinforcement learning of coordination in cooperative multiagent systems. In Proceedings of the 18th National Conference on Artificial Intelligence. 326--331.Google Scholar
- R. Makar, S. Mahadevan, and M. Ghavamzadeh. 2001. Hierarchical multi-agent reinforcement learning. In Proceedings of the 5th International Conference on Autonomous Agents. 246--253. Google Scholar
Digital Library
- J. Marchant, N. Griffiths, and M. Leeke. 2015. Manipulating conventions in a particle-based topology. In Proceedings of the Coordination, Organizations, Institutions and Norms in Agent Systems Workshop.Google Scholar
- M. Matlock and S. Sen. 2007. Effective tag mechanisms for evolving coordination. In Proceedings of the 6th International Joint Conference on Autonomous Agents and Multiagent Systems. ACM, 251. Google Scholar
Digital Library
- M. Matlock and S. Sen. 2009. Effective tag mechanisms for evolving cooperation. In Proceedings of the 8th International Conference on Autonomous Agents and Multiagent Systems. 489--496.Google Scholar
- M. Mihaylov, K. Tuyls, and A. Nowé. 2014. A decentralized approach for convention emergence in multi-agent systems. Autonomous Agents and Multi-Agent Systems 28, 5 (2014), 749–778.Google Scholar
Digital Library
- J. Morales, M. Lopez-Sanchez, J. A. Rodriguez-Aguilar, M. Wooldridge, and W. Vasconcelos. 2013. Automated synthesis of normative systems. In Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems. 483--490.Google Scholar
- R. Polikar. 2006. Ensemble based systems in decision making. Circ. Syst. Mag. 6, 3 (2006), 21--45. Google Scholar
Cross Ref
- S. Redner. 1998. How popular is your paper an empirical study of the citation distribution. Eur. Phys. J. B 4, 2 (1998), 132--134. Google Scholar
Cross Ref
- A. Réka and A. L. Barabási. 2002. Statistical mechanics of complex networks. Rev. Mod. Phys. 74, 1 (2002), 47--97.Google Scholar
Cross Ref
- O. Sen and S. Sen. 2010. Effects of social network topology and options on norm emergence. In Coordination, Organizations, Institutions and Norms in Agent Systems V. 211--222. Google Scholar
Cross Ref
- S. Sen and S. Airiau. 2007. Emergence of norms through social learning. In Proceedings of the 16th International Joint Conference on Artificial Intelligence. 1507--1512.Google Scholar
- Y. Shoham and M. Tennenholtz. 1997. On the emergence of social conventions: Modeling, analysis and simulations. Artif. Intell. 94(1-2) (1997), 139--166. Google Scholar
Digital Library
- D. Villatoro, J. Sabater-Mir, and S. Sen. 2011. Social instruments for robust convention emergence. In Proceedings of the 20th International Joint Conference on Artificial Intelligence. 420--425.Google Scholar
- D. Villatoro, S. Sen, and J. Sabater-Mir. 2009. Topology and memory effect on convention emergence. In Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, Volume 02. 233--240. Google Scholar
Digital Library
- X. F. Wang and G. R. Chen. 2003. Complex networks: Small-world, scale-free and beyond. IEEE Circ. Syst. Mag. 3, 1 (2003), 6--20. Google Scholar
Cross Ref
- T. P. Yang, Z. P. Meng, J. Y. Hao, S. Sen, and C. Yu. 2016. Accelerating norm emergence through hierarchical heuristic learning. In Proceedings of the 22th European Conference on Artificial Intelligence (ECAI’16). 1344--1352.Google Scholar
- H. P. Young. 1996. The economics of convention. J. Econ. Perspect. 10, 2 (1996), 105--122. Google Scholar
Cross Ref
- C. Yu, H. T. Lv, F. H. Ren, H. L. Bao, and J. Y. Hao. 2015. Hierarchical learning for emergence of social norms in networked multiagent systems. In AI 2015: Advances in Artificial Intelligence. Springer, Berlin, 630--643. Google Scholar
Cross Ref
- C. Yu, G. Z. Tan, H. T. Lv, Z. Wang, J. Meng, J. Y. Hao, and F. H. Ren. 2016. Modelling adaptive learning behaviours for consensus formation in human societies. Sci. Rep. 6 (2016). Google Scholar
Cross Ref
- C. Yu, M. J. Zhang, and F. H. Ren. 2014. Collective learning for the emergence of social norms in networked multiagent systems. IEEE Trans. Cybernet. 44, 12 (2014), 2342--2355. Google Scholar
Cross Ref
- C. Yu, M. J. Zhang, F. H. Ren, and X. D. Luo. 2013. Emergence of social norms through collective learning in networked agent societies. In Proceedings of the 12th International Conference on Autonomous Agents and Multiagent Systems. 475--482.Google Scholar
Index Terms
Efficient and Robust Emergence of Norms through Heuristic Collective Learning
Recommendations
Heuristic Collective Learning for Efficient and Robust Emergence of Social Norms
AAMAS '15: Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent SystemsIn multiagent systems, social norms is a useful technique in regulating agents' behaviors to achieve coordination or cooperation among agents. One important research question is to investigate how a desirable social norm can be evolved in a bottom-up ...
Emergence of social norms through collective learning in networked agent societies
AAMAS '13: Proceedings of the 2013 international conference on Autonomous agents and multi-agent systemsSocial norms play a pivotal role in sustaining social order by regulating individual behaviors in a society. In normative multiagent systems, social norms have been used as an efficient mechanism to govern virtual agent societies towards cooperation and ...
Norm Emergence in Multiagent Systems: A Viewpoint Paper
AAMAS '20: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent SystemsThe literature on norm emergence and normative MAS considers norms from two perspectives, namely: prescriptive norms using deontic concepts, and emergent norms that capture preference behaviour. We find that both perspectives lend themselves naturally ...






Comments