Abstract
Agents in Multi-Agent Systems (MAS) are not always built and controlled by the system designer, e.g., on electronic trading platforms. In this case, there is often a system objective which can differ from the agents’ own goals (e.g., price stability). While much effort has been put into modeling and optimizing agent behavior, we are concerned in this paper with the platform perspective. Our model extends Stochastic Games (SG) with dynamic restriction of action spaces to a new self-learning governance approach for black-box MAS. This governance learns an optimal restriction policy via Reinforcement Learning.
As an alternative to the two straight-forward approaches—fully centralized control and fully independent learners—, this novel method combines a sufficient degree of autonomy for the agents with selective restriction of their action spaces. We demonstrate that the governance, though not explicitly instructed to leave any freedom of decision to the agents, learns that combining the agents’ and its own capabilities is better than controlling all actions. As shown experimentally, the self-learning approach outperforms (w.r.t. the system objective) both “full control” where actions are always dictated without any agent autonomy, and “ungoverned MAS” where the agents simply pursue their individual goals.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abdunabi, T., Basir, O.: Holonic intelligent multi-agent algorithmic trading system (HIMAATS). Int. J. Comput. Appl. 21, 54–61 (2014)
Aires, J.P., Meneguzzi, F.: Norm conflict identification using deep learning. In: AAMAS Workshops (2017)
Aldewereld, H., Boissier, O., Dignum, V., Noriega, P., Padget, J. (eds.): Social Coordination Frameworks for Social Technical Systems. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-33570-4
Arcos, J.L., Esteva, M., Noriega, P., Rodríguez-Aguilar, J.A., Sierra, C.: Environment engineering for multiagent systems. In: Engineering Applications of Artificial Intelligence (2004)
Arcos, J.L., Rodríguez-Aguilar, J.A., Rosell, B.: Engineering autonomic electronic institutions. In: Weyns, D., Brueckner, S.A., Demazeau, Y. (eds.) EEMMAS 2007. LNCS (LNAI), vol. 5049, pp. 76–87. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-85029-8_6
Balke, T., et al.: Norms in MAS: definitions and related concepts, p. 31. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik (2013)
Barbuceanu, M.: Coordinating agents by role based social constraints and conversation plans. In: AAAI/IAAI (1997)
Boella, G., van der Torre, L., Verhagen, H.: Introduction to normative multiagent systems. Comput. Math. Organ. Theory 12(2), 71–79 (2006). https://doi.org/10.1007/s10588-006-9537-7
Boella, G., van der Torre, L., Verhagen, H.: Introduction to the special issue on normative multiagent systems. Auton. Agents Multi-Agent Syst. 17(1), 1–10 (2008). https://doi.org/10.1007/s10458-008-9047-8
Bou, E., López-Sánchez, M., Rodríguez-Aguilar, J.A.: Towards self-configuration in autonomic electronic institutions. In: Noriega, P., et al. (eds.) COIN 2006. LNCS (LNAI), vol. 4386, pp. 229–244. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74459-7_15
Cacciamani, F., Celli, A., Ciccone, M., Gatti, N.: Multi-agent coordination in adversarial environments through signal mediated strategies. In: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems. International Foundation for Autonomous Agents and Multiagent Systems, Richland (2021)
Cheung, W.C., Simchi-Levi, D., Zhu, R.: Reinforcement learning for non-stationary markov decision processes: the blessing of (more) optimism. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, Virtual Event, 13–18 July 2020 (2020)
Conitzer, V., Sandholm, T.: AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents. Mach. Learn. 67, 23–43 (2003). https://doi.org/10.1007/s10994-006-0143-1
Conte, R., Falcone, R., Sartor, G.: Introduction: agents and norms: how to fill the gap? Artif. Intell. Law 7(1), 1–15 (1999). https://doi.org/10.1023/A:1008397328506
Esteva, M., et al.: Electronic institutions development environment. In: AAMAS Demo Proceedings, vol. 3. International Foundation for Autonomous Agents and Multiagent Systems (2008)
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
Frantz, C., Pigozzi, G.: Modelling norm dynamics in multi-agent systems. J. Appl. Logic 5, 491–564 (2018)
Gomez-Sanz, J.J.: Ingenias. In: Aldewereld, H., Boissier, O., Dignum, V., Noriega, P., Padget, J. (eds.) Social Coordination Frameworks for Social Technical Systems. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-33570-4_5
Greenwald, A., Hall, K.: Correlated-Q learning. In: Proceedings of the Twentieth International Conference on International Conference on Machine Learning, ICML2003. AAAI Press (2003)
Gronauer, S., Diepold, K.: Multi-agent deep reinforcement learning: a survey. Artif. Intell. Rev. 55, 895–943 (2021). https://doi.org/10.1007/s10462-021-09996-w
Hwang, K., Jiang, W., Chen, Y.: Model learning and knowledge sharing for a multiagent system with Dyna-Q learning. IEEE Trans. Cybern. 45(5), 978–990 (2015)
Liang, E., et al.: RLlib: abstractions for distributed reinforcement learning. In: ICML (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. Morgan Kaufmann Publishers Inc., San Francisco (1994)
Lopes Cardoso, H., Urbano, J., Rocha, A., Castro, A.J.M., Oliveira, E.: ANTE: a framework integrating negotiation, norms and trust. In: ldewereld, H., Boissier, O., Dignum, V., Noriega, P., Padget, J. (eds.) Social Coordination Frameworks for Social Technical Systems, vol. 30. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-33570-4_3
Marín-Lora, C., Chover, M., Sotoca, J.M., García, L.A.: A game engine to make games as multi-agent systems. Adv. Eng. Softw. 140, 02732 (2020)
McGroarty, F., Booth, A., Gerding, E., Chinthalapati, V.L.R.: High frequency trading strategies, market fragility and price spikes: an agent based model perspective. Ann. Oper. Res. 282(1), 217–244 (2019). https://doi.org/10.1007/s10479-018-3019-4
Mellema, R., Jensen, M., Dignum, F.: Social rules for agent systems. In: Aler Tubella, A., Cranefield, S., Frantz, C., Meneguzzi, F., Vasconcelos, W. (eds.) COIN/COINE 2017/2020. LNCS (LNAI), vol. 12298, pp. 175–180. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-72376-7_10
Morales, J.: On-line norm synthesis for open Multi-Agent systems. Ph.D. thesis, Universitat de Barcelona (2016)
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
Noriega, P.: Agent-mediated auctions: the fishmarket metaphor. Ph.D. thesis, Universitat Autonoma de Barcelona (1997)
Noriega, P., de Jonge, D.: Electronic institutions: the EI/EIDE framework. In: Aldewereld, H., Boissier, O., Dignum, V., Noriega, P., Padget, J. (eds.) Social Coordination Frameworks for Social Technical Systems. LGTS, vol. 30, pp. 47–76. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-33570-4_4
Nowé, A., Vrancx, P., De Hauwere, Y.M.: Game theory and multi-agent reinforcement learning. In: Wiering, M., van Otterlo, M. (eds.) Reinforcement Learning: State-of-the-Art. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-27645-3_14
Padakandla, S., K. J., P., Bhatnagar, S.: Reinforcement learning algorithm for non-stationary environments. Appl. Intell. 50(11), 3590–3606 (2020). https://doi.org/10.1007/s10489-020-01758-5
Riad, M., Golpayegani, F.: Run-time norms synthesis in multi-objective multi-agent systems. In: Theodorou, A., Nieves, J.C., De Vos, M. (eds.) COINE 2021. LNCS, vol. 13239, pp. 78–93. Springer, Cham (2021). https://doi.org/10.1007/978-3-031-16617-4_6
Rizk, Y., Awad, M., Tunstel, E.: Decision making in multi-agent systems: a survey. IEEE Trans. Cogn. Dev. Syst. 10, 514–529 (2018)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017)
Shoham, Y., Tennenholtz, M.: On social laws for artificial agent societies: off-line design. Artif. Intell. 73(1), 231–252 (1995)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (2018)
Wang, X., Sandholm, T.: Reinforcement learning to play an optimal nash equilibrium in team Markov games. In: NIPS (2002)
Weyns, D., Brückner, S., Demazeau, Y.: Engineering Environment-Mediated Multi-Agent Systems. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-85029-8
Zaib, M., Sheng, Q.Z., Zhang, W.E.: A short survey of pre-trained language models for conversational AI-A NewAge in NLP (2021)
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
Zinkevich, M., Greenwald, A., Littman, M.L.: Cyclic equilibria in Markov games. In: Proceedings of the 18th International Conference on Neural Information Processing Systems, NIPS 2005. MIT Press, Cambridge (2005)
Acknowledgements
This work is supported by the German Federal Ministry for Economic Affairs and Energy (BMWi).
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
Oesterle, M., Bartelt, C., Lüdtke, S., Stuckenschmidt, H. (2022). Self-learning Governance of Black-Box Multi-Agent Systems. 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_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-20845-4_5
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)