Abstract
This paper explores the emergence of norms in agents’ societies when agents play multiple - even incompatible - roles in their social contexts simultaneously, and have limited interaction ranges. Specifically, this article proposes two reinforcement learning methods for agents to compute agreements on strategies for using common resources to perform joint tasks. The computation of norms by considering agents’ playing multiple roles in their social contexts has not been studied before. To make the problem even more realistic for open societies, we do not assume that agents share knowledge on their common resources. So, they have to compute semantic agreements towards performing their joint actions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Of course agents may specify periods using different time granularities, different forms of representing time, etc. In this paper we assume that there is a specific granularity for specifying periods and thus agents just have to align their specifications: Otherwise, further agreements are necessary.
- 2.
It must be pointed out that since the neighborhood of any agent includes itself, and its social context includes its own roles, it may also hold that \(i=j\).
- 3.
the notation (\(\cdot \textit{:m}\)) means “any agent playing the role \(R_m\)”.
References
Epstein, J.: Learning to be thoughtless: social norms and individual computation. Comput. Econ. 18(1), 9–24 (2001)
Mukherjee, P., Sen, S., Airiau, S.: Norm emergence under constrained interactions in diverse societies. In: Padgham, L., Parkes, D.C., Müller, J.P., Parsons, S. (eds.) AAMAS (2), pp. 779–786. IFAAMAS (2008)
Sen, S., Airiau, S.: Emergence of norms through social learning. In: Proceedings of the 20th International Joint Conference on Artifical Intelligence, IJCAI 2007, pp. 1507–1512. Morgan Kaufmann Publishers Inc., San Francisco (2007)
Yu, C., Zhang, M., Ren, F., Luo, X.: Emergence of social norms through collective learning in networked agent societies. In: Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems, AAMAS 2013, pp. 475–482. International Foundation for Autonomous Agents and Multiagent Systems, Richland (2013)
Vouros, G.: Decentralized semantic coordination via belief propagation. In: Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems, AAMAS 2013, pp. 1207–1208. International Foundation for Autonomous Agents and Multiagent Systems, Richland (2013)
Puterman, M.L.: Markov Decision Processes: Discrete Stochastic Dynamic Programming, 1st edn. Wiley, New York (1994)
Guestrin, C.E.: Planning under uncertainty in complex structured environments. Ph.D. thesis, Stanford, CA, USA (2003) AAI3104233
Guestrin, C.G., Lagoudakis, M., Parr, R.: Coordinated reinforcement learning. In: Proceedings of the ICML-2002 The Nineteenth International Conference on Machine Learning, pp. 227–234 (2002)
Kok, J.R., Vlassis, N.: Collaborative multiagent reinforcement learning by payoff propagation. J. Mach. Learn. Res. 7, 1789–1828 (2006)
Watts, D.J., Strogatz, S.H.: Collective dynamics of ‘small-world’ networks. Nature 393(6684), 440–442 (1998)
Albert, R., Lászl Barabási, A.: Statistical mechanics of complex networks. Rev. Mod. Phys. 74, 47–97 (2002)
Savarimuthu, B.T.R.: Norm learning in multi-agent societies. Information Science Discussion Papers Series No. 2011/05 (2011). http://hdl.handle.net/10523/1690 (retrieved)
Shoham, Y., Tennenholtz, M.: On the emergence of social conventions: modeling, analysis, and simulations. Artif. Intell. 94(1–2), 139–166 (1997)
Villatoro, D., Sabater-Mir, J., Sen, S.: Social instruments for robust convention emergence. In: Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence, IJCAI 2011, vol. 1, pp. 420–425. AAAI Press (2011)
Villatoro, D., Sen, S., Sabater-Mir, J.: 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, WI-IAT 2009, vol. 02, pp. 233–240. IEEE Computer Society, Washington, DC (2009)
Sen, O., Sen, S.: Effects of social network topology and options on norm emergence. In: Padget, J., Artikis, A., Vasconcelos, W., Stathis, K., da Silva, V.T., Matson, E., Polleres, A. (eds.) COIN@AAMAS 2009. LNCS, vol. 6069, pp. 211–222. Springer, Heidelberg (2010)
Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artif. Intell. 136, 215–250 (2002)
Fudenberg, D., Levine, D.: The Theory in Learning in Games. The MIT Press, Cambridge (1998)
Barto, A.G., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discrete Event Dyn. Syst. 13(1–2), 41–77 (2003)
Acknowledgement
The publication of this article has been partially supported by the University of Piraeus Research Center.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Vouros, G.A. (2015). The Emergence of Norms via Contextual Agreements in Open Societies. In: Koch, F., Guttmann, C., Busquets, D. (eds) Advances in Social Computing and Multiagent Systems. MFSC 2015. Communications in Computer and Information Science, vol 541. Springer, Cham. https://doi.org/10.1007/978-3-319-24804-2_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-24804-2_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24803-5
Online ISBN: 978-3-319-24804-2
eBook Packages: Computer ScienceComputer Science (R0)