{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T19:36:26Z","timestamp":1743017786043,"version":"3.40.3"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031208447"},{"type":"electronic","value":"9783031208454"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20845-4_5","type":"book-chapter","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T14:46:31Z","timestamp":1669301191000},"page":"73-91","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-learning Governance of Black-Box Multi-Agent Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6939-1028","authenticated-orcid":false,"given":"Michael","family":"Oesterle","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0426-6714","authenticated-orcid":false,"given":"Christian","family":"Bartelt","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1488-4236","authenticated-orcid":false,"given":"Stefan","family":"L\u00fcdtke","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0209-3859","authenticated-orcid":false,"given":"Heiner","family":"Stuckenschmidt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,24]]},"reference":[{"key":"5_CR1","first-page":"54","volume":"21","author":"T Abdunabi","year":"2014","unstructured":"Abdunabi, T., Basir, O.: Holonic intelligent multi-agent algorithmic trading system (HIMAATS). Int. J. Comput. Appl. 21, 54\u201361 (2014)","journal-title":"Int. J. Comput. Appl."},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Aires, J.P., Meneguzzi, F.: Norm conflict identification using deep learning. In: AAMAS Workshops (2017)","DOI":"10.1007\/978-3-319-71679-4_13"},{"key":"5_CR3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-33570-4","volume-title":"Social Coordination Frameworks for Social Technical Systems","year":"2016","unstructured":"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"},{"key":"5_CR4","unstructured":"Arcos, J.L., Esteva, M., Noriega, P., Rodr\u00edguez-Aguilar, J.A., Sierra, C.: Environment engineering for multiagent systems. In: Engineering Applications of Artificial Intelligence (2004)"},{"key":"5_CR5","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1007\/978-3-540-85029-8_6","volume-title":"Engineering Environment-Mediated Multi-Agent Systems","author":"JL Arcos","year":"2008","unstructured":"Arcos, J.L., Rodr\u00edguez-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\u201387. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-85029-8_6"},{"key":"5_CR6","unstructured":"Balke, T., et al.: Norms in MAS: definitions and related concepts, p. 31. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik (2013)"},{"key":"5_CR7","unstructured":"Barbuceanu, M.: Coordinating agents by role based social constraints and conversation plans. In: AAAI\/IAAI (1997)"},{"issue":"2","key":"5_CR8","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1007\/s10588-006-9537-7","volume":"12","author":"G Boella","year":"2006","unstructured":"Boella, G., van der Torre, L., Verhagen, H.: Introduction to normative multiagent systems. Comput. Math. Organ. Theory 12(2), 71\u201379 (2006). https:\/\/doi.org\/10.1007\/s10588-006-9537-7","journal-title":"Comput. Math. Organ. Theory"},{"issue":"1","key":"5_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10458-008-9047-8","volume":"17","author":"G Boella","year":"2008","unstructured":"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\u201310 (2008). https:\/\/doi.org\/10.1007\/s10458-008-9047-8","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"5_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/978-3-540-74459-7_15","volume-title":"Coordination, Organizations, Institutions, and Norms in Agent Systems II","author":"E Bou","year":"2007","unstructured":"Bou, E., L\u00f3pez-S\u00e1nchez, M., Rodr\u00edguez-Aguilar, J.A.: Towards self-configuration in autonomic electronic institutions. In: Noriega, P., et al. (eds.) COIN 2006. LNCS (LNAI), vol. 4386, pp. 229\u2013244. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-74459-7_15"},{"key":"5_CR11","unstructured":"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)"},{"key":"5_CR12","unstructured":"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\u201318 July 2020 (2020)"},{"key":"5_CR13","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10994-006-0143-1","volume":"67","author":"V Conitzer","year":"2003","unstructured":"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\u201343 (2003). https:\/\/doi.org\/10.1007\/s10994-006-0143-1","journal-title":"Mach. Learn."},{"issue":"1","key":"5_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1023\/A:1008397328506","volume":"7","author":"R Conte","year":"1999","unstructured":"Conte, R., Falcone, R., Sartor, G.: Introduction: agents and norms: how to fill the gap? Artif. Intell. Law 7(1), 1\u201315 (1999). https:\/\/doi.org\/10.1023\/A:1008397328506","journal-title":"Artif. Intell. Law"},{"key":"5_CR15","unstructured":"Esteva, M., et al.: Electronic institutions development environment. In: AAMAS Demo Proceedings, vol. 3. International Foundation for Autonomous Agents and Multiagent Systems (2008)"},{"key":"5_CR16","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/3-540-44682-6_8","volume-title":"Agent Mediated Electronic Commerce","author":"M Esteva","year":"2001","unstructured":"Esteva, M., Rodr\u00edguez-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\u2013147. Springer, Heidelberg (2001). https:\/\/doi.org\/10.1007\/3-540-44682-6_8"},{"key":"5_CR17","first-page":"491","volume":"5","author":"C Frantz","year":"2018","unstructured":"Frantz, C., Pigozzi, G.: Modelling norm dynamics in multi-agent systems. J. Appl. Logic 5, 491\u2013564 (2018)","journal-title":"J. Appl. Logic"},{"key":"5_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-33570-4_5","volume-title":"Social Coordination Frameworks for Social Technical Systems","author":"JJ Gomez-Sanz","year":"2016","unstructured":"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"},{"key":"5_CR19","unstructured":"Greenwald, A., Hall, K.: Correlated-Q learning. In: Proceedings of the Twentieth International Conference on International Conference on Machine Learning, ICML2003. AAAI Press (2003)"},{"key":"5_CR20","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","volume":"55","author":"S Gronauer","year":"2021","unstructured":"Gronauer, S., Diepold, K.: Multi-agent deep reinforcement learning: a survey. Artif. Intell. Rev. 55, 895\u2013943 (2021). https:\/\/doi.org\/10.1007\/s10462-021-09996-w","journal-title":"Artif. Intell. Rev."},{"issue":"5","key":"5_CR21","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TCYB.2014.2341582","volume":"45","author":"K Hwang","year":"2015","unstructured":"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\u2013990 (2015)","journal-title":"IEEE Trans. Cybern."},{"key":"5_CR22","unstructured":"Liang, E., et al.: RLlib: abstractions for distributed reinforcement learning. In: ICML (2018)"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"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)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"5_CR24","doi-asserted-by":"publisher","unstructured":"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.\u00a030. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-33570-4_3","DOI":"10.1007\/978-3-319-33570-4_3"},{"key":"5_CR25","doi-asserted-by":"publisher","first-page":"02732","DOI":"10.1016\/j.advengsoft.2019.102732","volume":"140","author":"C Mar\u00edn-Lora","year":"2020","unstructured":"Mar\u00edn-Lora, C., Chover, M., Sotoca, J.M., Garc\u00eda, L.A.: A game engine to make games as multi-agent systems. Adv. Eng. Softw. 140, 02732 (2020)","journal-title":"Adv. Eng. Softw."},{"issue":"1","key":"5_CR26","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/s10479-018-3019-4","volume":"282","author":"F McGroarty","year":"2019","unstructured":"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\u2013244 (2019). https:\/\/doi.org\/10.1007\/s10479-018-3019-4","journal-title":"Ann. Oper. Res."},{"key":"5_CR27","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1007\/978-3-030-72376-7_10","volume-title":"Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XIII","author":"R Mellema","year":"2021","unstructured":"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\u2013180. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72376-7_10"},{"key":"5_CR28","unstructured":"Morales, J.: On-line norm synthesis for open Multi-Agent systems. Ph.D. thesis, Universitat de Barcelona (2016)"},{"key":"5_CR29","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1007\/978-3-030-79876-5_32","volume-title":"Automated Deduction \u2013 CADE 28","author":"E Neufeld","year":"2021","unstructured":"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\u2013576. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-79876-5_32"},{"key":"5_CR30","unstructured":"Noriega, P.: Agent-mediated auctions: the fishmarket metaphor. Ph.D. thesis, Universitat Autonoma de Barcelona (1997)"},{"key":"5_CR31","series-title":"Law, Governance and Technology Series","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1007\/978-3-319-33570-4_4","volume-title":"Social Coordination Frameworks for Social Technical Systems","author":"P Noriega","year":"2016","unstructured":"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\u201376. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-33570-4_4"},{"key":"5_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_14","volume-title":"Reinforcement Learning: State-of-the-Art","author":"A Now\u00e9","year":"2012","unstructured":"Now\u00e9, 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"},{"key":"5_CR33","doi-asserted-by":"publisher","unstructured":"Padakandla, S., K. J., P., Bhatnagar, S.: Reinforcement learning algorithm for non-stationary environments. Appl. Intell. 50(11), 3590\u20133606 (2020). https:\/\/doi.org\/10.1007\/s10489-020-01758-5","DOI":"10.1007\/s10489-020-01758-5"},{"key":"5_CR34","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1007\/978-3-031-16617-4_6","volume-title":"COINE 2021","author":"M Riad","year":"2021","unstructured":"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\u201393. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-031-16617-4_6"},{"key":"5_CR35","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1109\/TCDS.2018.2840971","volume":"10","author":"Y Rizk","year":"2018","unstructured":"Rizk, Y., Awad, M., Tunstel, E.: Decision making in multi-agent systems: a survey. IEEE Trans. Cogn. Dev. Syst. 10, 514\u2013529 (2018)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"5_CR36","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms (2017)"},{"issue":"1","key":"5_CR37","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/0004-3702(94)00007-N","volume":"73","author":"Y Shoham","year":"1995","unstructured":"Shoham, Y., Tennenholtz, M.: On social laws for artificial agent societies: off-line design. Artif. Intell. 73(1), 231\u2013252 (1995)","journal-title":"Artif. Intell."},{"key":"5_CR38","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. A Bradford Book, Cambridge (2018)"},{"key":"5_CR39","unstructured":"Wang, X., Sandholm, T.: Reinforcement learning to play an optimal nash equilibrium in team Markov games. In: NIPS (2002)"},{"key":"5_CR40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85029-8","volume-title":"Engineering Environment-Mediated Multi-Agent Systems","author":"D Weyns","year":"2007","unstructured":"Weyns, D., Br\u00fcckner, S., Demazeau, Y.: Engineering Environment-Mediated Multi-Agent Systems. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-85029-8"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Zaib, M., Sheng, Q.Z., Zhang, W.E.: A short survey of pre-trained language models for conversational AI-A NewAge in NLP (2021)","DOI":"10.1145\/3373017.3373028"},{"key":"5_CR42","series-title":"Studies in Systems, Decision and Control","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/978-3-030-60990-0_12","volume-title":"Handbook of Reinforcement Learning and Control","author":"K Zhang","year":"2021","unstructured":"Zhang, K., Yang, Z., Ba\u015far, 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\u2013384. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-60990-0_12"},{"key":"5_CR43","unstructured":"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)"}],"container-title":["Lecture Notes in Computer Science","Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems XV"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20845-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T14:49:25Z","timestamp":1669301365000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20845-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031208447","9783031208454"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20845-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"24 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"COINE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Coordination, Organizations, Institutions, Norms, and Ethics for Governance of Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 May 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 May 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"coin2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/coin-workshop.github.io\/coine-2022-auckland\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}