Abstract
Mixed-motive games comprise a subset of games in which individual and collective incentives are not entirely aligned. These games are relevant because they frequently occur in real-world and artificial societies, and their outcome is often bad for the involved parties. Institutions and norms offer a good solution for governing mixed-motive systems. Still, they are usually incorporated into the system in a distributed fashion, or they are not able to dynamically adjust to the needs of the environment at run-time. We propose a way of reaching socially good outcomes in mixed-motive multiagent reinforcement learning settings by enhancing the environment with a normative system controlled by an external reinforcement learning agent. By adopting this proposal, we show it is possible to reach social welfare in a mixed-motive system of self-interested agents using only traditional reinforcement learning agent architectures.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
By traditional RL agent architectures we mean commonly used in other RL tasks such as A2C [21].
- 4.
All relevant code and data for this project is available at https://github.com/rafacheang/social_dilemmas_regulation.
- 5.
References
Bou, E., López-Sánchez, M., Rodríguez-Aguilar, J.A., Sichman, J.S.: Adapting autonomic electronic institutions to heterogeneous agent societies. In: Vouros, G., Artikis, A., Stathis, K., Pitt, J. (eds.) OAMAS 2008. LNCS (LNAI), vol. 5368, pp. 18–35. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-02377-4_2
Bou, E., López-Sánchez, M., Rodríguez-Aguilar, J.A.: Towards self-configuration in autonomic electronic institutions. In: Noriega, P., Vázquez-Salceda, J., Boella, G., Boissier, O., Dignum, V., Fornara, N., Matson, E. (eds.) COIN 2006. LNCS (LNAI), vol. 4386, pp. 229–244. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74459-7_15
Brockman, G., et al.: OpenAI Gym. arXiv preprint arXiv:1606.01540 (2016)
Cardoso, H.L., Oliveira, E.: Adaptive deterrence sanctions in a normative framework. In: Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, pp. 36–43. IEEE Computer Society (2009)
Castelfranchi, C.: Engineering social order. In: Omicini, A., Tolksdorf, R., Zambonelli, F. (eds.) ESAW 2000. LNCS (LNAI), vol. 1972, pp. 1–18. Springer, Heidelberg (2000). https://doi.org/10.1007/3-540-44539-0_1
Conte, R.: Emergent (info)institutions. Cogn. Syst. Res. 2(2), 97–110 (2001). https://doi.org/10.1016/S1389-0417(01)00020-1
Crawford, S.E.S., Ostrom, E.: A grammar of institutions. Am. Polit. Sci. Rev. 89(3), 582–600 (1995). https://doi.org/10.2307/2082975
Dawes, R.M.: Social dilemmas. Annu. Rev. Psychol. 31(1), 169–193 (1980). https://doi.org/10.1146/annurev.ps.31.020180.001125
Eccles, T., Hughes, E., Kramár, J., Wheelwright, S., Leibo, J.Z.: Learning reciprocity in complex sequential social dilemmas (2019)
Esteva, M., de la Cruz, D., Rosell, B., Arcos, J.L., Rodríguez-Aguilar, J., Cuní, G.: Engineering open multi-agent systems as electronic institutions. In: Proceedings of the 19th National Conference on Artificial Intelligence, AAAI 2004, pp. 1010–1011. AAAI Press (01 2004)
Esteva, M., Rodríguez-Aguilar, J.-A., Sierra, C., Garcia, P., Arcos, J.L.: On the formal specification of electronic institutions. In: Dignum, F., Sierra, C. (eds.) Agent Mediated Electronic Commerce. LNCS (LNAI), vol. 1991, pp. 126–147. Springer, Heidelberg (2001). https://doi.org/10.1007/3-540-44682-6_8
Ghorbani, A., Ho, P., Bravo, G.: Institutional form versus function in a common property context: the credibility thesis tested through an agent-based model. Land Use Policy 102, 105237 (2021). https://doi.org/10.1016/j.landusepol.2020.105237. https://www.sciencedirect.com/science/article/pii/S0264837720325758
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 80, pp. 1861–1870. PMLR, 10–15 July 2018. https://proceedings.mlr.press/v80/haarnoja18b.html
Hardin, G.: The tragedy of the commons. Science 162(3859), 1243–1248 (1968). https://doi.org/10.1126/science.162.3859.1243. https://science.sciencemag.org/content/162/3859/1243
Hughes, E., et al.: Inequity aversion improves cooperation in intertemporal social dilemmas. In: Bengio, S., Wallach, H., Larochelle, H., Grauman, K., Cesa-Bianchi, N., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 31. Curran Associates, Inc. (2018). https://proceedings.neurips.cc/paper/2018/file/7fea637fd6d02b8f0adf6f7dc36aed93-Paper.pdf
Jones, A.J.I., Sergot, M.: On the characterization of law and computer systems: the normative systems perspective, pp. 275–307. Wiley, Chichester (1994)
Kollock, P.: Social dilemmas: the anatomy of cooperation. Annu. Rev. Sociol. 24(1), 183–214 (1998). https://doi.org/10.1146/annurev.soc.24.1.183
Lerer, A., Peysakhovich, A.: Maintaining cooperation in complex social dilemmas using deep reinforcement learning (2018)
Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the Eleventh International Conference on International Conference on Machine Learning, ICML 1994, pp. 157–163. Morgan Kaufmann Publishers Inc., San Francisco (1994)
McKee, K.R., Gemp, I., McWilliams, B., Duèñez Guzmán, E.A., Hughes, E., Leibo, J.Z.: Social diversity and social preferences in mixed-motive reinforcement learning. In: Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2020, pp. 869–877. International Foundation for Autonomous Agents and Multiagent Systems, Richland (2020)
Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of The 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 48, pp. 1928–1937. PMLR, New York, 20–22 June 2016. https://proceedings.mlr.press/v48/mniha16.html
Nardin, L.G.: An adaptive sanctioning enforcement model for normative multiagent systems. Ph.D. thesis, Universidade de São Paulo (2015)
Neufeld, E., Bartocci, E., Ciabattoni, A., Governatori, G.: A normative supervisor for reinforcement learning agents. In: Platzer, A., Sutcliffe, G. (eds.) CADE 2021. LNCS (LNAI), vol. 12699, pp. 565–576. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-79876-5_32
Olson, M.: The Logic of Collective Action: Public Goods and the Theory of Groups. Harvard Economic Studies, vol. 124, p. 176. Harvard University Press, Cambridge (1965). https://www.hup.harvard.edu/catalog.php?isbn=9780674537514
Ostrom, E.: Coping with tragedies of the commons. Annu. Rev. Polit. Sci. 2(1), 493–535 (1999). https://doi.org/10.1146/annurev.polisci.2.1.493
Ostrom, E.: Collective action and the evolution of social norms. J. Econ. Perspect. 14(3), 137–158 (2000). https://doi.org/10.1257/jep.14.3.137
Pérolat, J., Leibo, J.Z., Zambaldi, V., Beattie, C., Tuyls, K., Graepel, T.: A multi-agent reinforcement learning model of common-pool resource appropriation. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017). https://proceedings.neurips.cc/paper/2017/file/2b0f658cbffd284984fb11d90254081f-Paper.pdf
Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1–8 (2021). http://jmlr.org/papers/v22/20-1364.html
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press, Cambridge (2018)
Terry, J.K., et al.: PettingZoo: a standard API for multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems (2021). https://proceedings.neurips.cc//paper/2021/file/7ed2d3454c5eea71148b11d0c25104ff-Paper.pdf
Ullmann-Margalit, E.: The Emergence of Norms. Oxford University Press, Oxford (1977)
Zhang, K., Yang, Z., Başar, T.: Multi-agent reinforcement learning: a selective overview of theories and algorithms. In: Vamvoudakis, K.G., Wan, Y., Lewis, F.L., Cansever, D. (eds.) Handbook of Reinforcement Learning and Control. SSDC, vol. 325, pp. 321–384. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-60990-0_12
Zheng, S., et al.: The AI economist: improving equality and productivity with AI-driven tax policies (2020)
Acknowledgements
This research is being carried out with the support of Itaú Unibanco S.A., through the scholarship program of Programa de Bolsas Itaú (PBI), and it is also financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES), Finance Code 001, Brazil.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cheang, R.M., Brandão, A.A.F., Sichman, J.S. (2022). Centralized Norm Enforcement in Mixed-Motive Multiagent Reinforcement Learning. In: Ajmeri, N., Morris Martin, A., Savarimuthu, B.T.R. (eds) Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XV. COINE 2022. Lecture Notes in Computer Science(), vol 13549. Springer, Cham. https://doi.org/10.1007/978-3-031-20845-4_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-20845-4_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20844-7
Online ISBN: 978-3-031-20845-4
eBook Packages: Computer ScienceComputer Science (R0)