{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:24:37Z","timestamp":1742919877578,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030822538"},{"type":"electronic","value":"9783030822545"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-82254-5_2","type":"book-chapter","created":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T22:02:32Z","timestamp":1626732152000},"page":"19-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Governing Black-Box Agents in Competitive Multi-Agent Systems"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6939-1028","authenticated-orcid":false,"given":"Michael","family":"Pernpeintner","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\/0000-0002-0209-3859","authenticated-orcid":false,"given":"Heiner","family":"Stuckenschmidt","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,7,20]]},"reference":[{"doi-asserted-by":"publisher","unstructured":"Andrighetto, G., Governatori, G., Noriega, P., van der Torre, L.: Normative multi-agent systems (2013). https:\/\/doi.org\/10.4230\/DFU.Vol4.12111.i","key":"2_CR1","DOI":"10.4230\/DFU.Vol4.12111.i"},{"unstructured":"Asadi, M., Huber, M.: State space reduction for hierarchical reinforcement learning, January 2004","key":"2_CR2"},{"doi-asserted-by":"crossref","unstructured":"Bade, S.: Nash equilibrium in games with incomplete preferences. Econ. Theory 26(2), 309\u2013332 (2005). www.jstor.org\/stable\/25055952","key":"2_CR3","DOI":"10.1007\/s00199-004-0541-1"},{"unstructured":"Balke, T., et al.: Norms in MAS: definitions and related concepts, p. 31, January 2013","key":"2_CR4"},{"issue":"2","key":"2_CR5","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":"2_CR6","first-page":"477","volume":"4","author":"RI Brafman","year":"1996","unstructured":"Brafman, R.I., Tennenholtz, M.: On partially controlled multi-agent systems. J. Artif. Int. Res. 4(1), 477\u2013507 (1996)","journal-title":"J. Artif. Int. Res."},{"issue":"C","key":"2_CR7","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.artint.2016.07.001","volume":"239","author":"N Bulling","year":"2016","unstructured":"Bulling, N., Dastani, M.: Norm-based mechanism design. Artif. Intell. 239(C), 97\u2013142 (2016). https:\/\/doi.org\/10.1016\/j.artint.2016.07.001","journal-title":"Artif. Intell."},{"unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National\/Tenth Conference on Artificial Intelligence\/Innovative Applications of Artificial Intelligence, AAAI 1998\/IAAI 1998, pp. 746\u2013752. American Association for Artificial Intelligence, Menlo Park (1998). http:\/\/dl.acm.org\/citation.cfm?id=295240.295800","key":"2_CR8"},{"unstructured":"Dean, T., Givan, R., Leach, S.: Model reduction techniques for computing approximately optimal solutions for Markov decision processes. In: Proceedings of the Thirteenth Conference on Uncertainty in Artificial Intelligence, pp. 124\u2013131. UAI 1997, Morgan Kaufmann Publishers Inc., San Francisco (1997)","key":"2_CR9"},{"unstructured":"Dell\u2019Anna, D., Dastani, M., Dalpiaz, F.: Runtime revision of norms and sanctions based on agent preferences. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2019, pp. 1609\u20131617. International Foundation for Autonomous Agents and Multiagent Systems, Richland (2019). Event-place: Montreal QC, Canada","key":"2_CR10"},{"doi-asserted-by":"publisher","unstructured":"Durugkar, I., Liebman, E., Stone, P.: Balancing individual preferences and shared objectives in multiagent reinforcement learning, p. 2483, July 2020. https:\/\/doi.org\/10.24963\/ijcai.2020\/343","key":"2_CR11","DOI":"10.24963\/ijcai.2020\/343"},{"issue":"1","key":"2_CR12","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/S0004-3702(00)00006-0","volume":"119","author":"D Fitoussi","year":"2000","unstructured":"Fitoussi, D., Tennenholtz, M.: Choosing social laws for multi-agent systems: minimality and simplicity. Artif. Intell. 119(1), 61\u2013101 (2000)","journal-title":"Artif. Intell."},{"doi-asserted-by":"crossref","unstructured":"Garc\u00eda-Camino, A., Rodr\u00edguez-Aguilar, J., Sierra, C., Vasconcelos, W.: A rule-based approach to norm-oriented programming of electronic institutions. SIGecom Exchanges 5, 33\u201340 (2006)","key":"2_CR13","DOI":"10.1145\/1124566.1124571"},{"key":"2_CR14","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1016\/j.ic.2018.02.023","volume":"261","author":"J Gutierrez","year":"2018","unstructured":"Gutierrez, J., Perelli, G., Wooldridge, M.: Imperfect information in reactive modules games. Inf. Comput. 261, 650\u2013675 (2018)","journal-title":"Inf. Comput."},{"issue":"6","key":"2_CR15","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1007\/s10458-019-09421-1","volume":"33","author":"P Hernandez-Leal","year":"2019","unstructured":"Hernandez-Leal, P., Kartal, B., Taylor, M.E.: A survey and critique of multiagent deep reinforcement learning. Auton. Agent. Multi-Agent Syst. 33(6), 750\u2013797 (2019). https:\/\/doi.org\/10.1007\/s10458-019-09421-1","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"2_CR16","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/11691839_1","volume-title":"Learning and Adaption in Multi-Agent Systems","author":"PJ Hoen","year":"2006","unstructured":"Hoen, P.J., Tuyls, K., Panait, L., Luke, S., La Poutr\u00e9, J.A.: An overview of cooperative and competitive multiagent learning. In: Tuyls, K., Hoen, P.J., Verbeeck, K., Sen, S. (eds.) LAMAS 2005. LNCS (LNAI), vol. 3898, pp. 1\u201346. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11691839_1"},{"issue":"3","key":"2_CR17","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1109\/TITS.2005.853695","volume":"6","author":"S Kim","year":"2005","unstructured":"Kim, S., Lewis, M.E., White, C.C.: State space reduction for nonstationary stochastic shortest path problems with real-time traffic information. IEEE Trans. Intell. Transp. Syst. 6(3), 273\u2013284 (2005). https:\/\/doi.org\/10.1109\/TITS.2005.853695","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"doi-asserted-by":"publisher","unstructured":"Koriche, F., Zanuttini, B.: Learning conditional preference networks. Artif. Intell. 174(11), 685\u2013703 (2010). https:\/\/doi.org\/10.1016\/j.artint.2010.04.019. http:\/\/www.sciencedirect.com\/science\/article\/pii\/S000437021000055X","key":"2_CR18","DOI":"10.1016\/j.artint.2010.04.019"},{"unstructured":"Lecarpentier, E., Rachelson, E.: Non-stationary Markov decision processes a worst-case approach using model-based reinforcement learning, April 2019","key":"2_CR19"},{"key":"2_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/978-3-642-27737-5_522-2","volume-title":"Encyclopedia of Complexity and Systems Science","author":"YJ Levy","year":"2017","unstructured":"Levy, Y.J., Solan, E.: Stochastic games. In: Meyers, R.A. (ed.) Encyclopedia of Complexity and Systems Science, pp. 1\u201323. Springer, Heidelberg (2017). https:\/\/doi.org\/10.1007\/978-3-642-27737-5_522-2"},{"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, ICML1994, pp. 157\u2013163. Morgan Kaufmann Publishers Inc., San Francisco (1994)","key":"2_CR21","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"issue":"6","key":"2_CR22","doi-asserted-by":"publisher","first-page":"4151","DOI":"10.1109\/TCOMM.2019.2899620","volume":"67","author":"L Liu","year":"2019","unstructured":"Liu, L., Chattopadhyay, A., Mitra, U.: On solving MDPs with large state space: exploitation of policy structures and spectral properties. IEEE Trans. Commun. 67(6), 4151\u20134165 (2019). https:\/\/doi.org\/10.1109\/TCOMM.2019.2899620","journal-title":"IEEE Trans. Commun."},{"key":"2_CR23","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1137\/18M1177615","volume":"57","author":"T Liu","year":"2019","unstructured":"Liu, T., Wang, J., Zhang, X., Cheng, D.: Game theoretic control of multiagent systems. SIAM J. Control. Optim. 57, 1691\u20131709 (2019)","journal-title":"SIAM J. Control. Optim."},{"issue":"1","key":"2_CR24","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1613\/jair.1.11261","volume":"63","author":"S L\u00fcdtke","year":"2018","unstructured":"L\u00fcdtke, S., Schr\u00f6der, M., Kr\u00fcger, F., Bader, S., Kirste, T.: State-space abstractions for probabilistic inference: a systematic review. J. Artif. Int. Res. 63(1), 789\u2013848 (2018). https:\/\/doi.org\/10.1613\/jair.1.11261","journal-title":"J. Artif. Int. Res."},{"doi-asserted-by":"crossref","unstructured":"Majeed, S.J., Hutter, M.: Exact reduction of huge action spaces in general reinforcement learning (2020)","key":"2_CR25","DOI":"10.1609\/aaai.v35i10.17074"},{"volume-title":"Deontic Logic in Computer Science: Normative System Specification","year":"1994","unstructured":"Meyer, J.J.C., Wieringa, R.J. (eds.): Deontic Logic in Computer Science: Normative System Specification. Wiley, USA (1994)","key":"2_CR26"},{"unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning,ICML2016, vol. 48. pp. 1928\u20131937. JMLR.org (2016)","key":"2_CR27"},{"key":"2_CR28","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529\u201333 (2015)","journal-title":"Nature"},{"unstructured":"Morales, J.: On-line norm synthesis for open multi-agent systems. Ph.D. thesis, Universitat de Barcelona (2016)","key":"2_CR29"},{"issue":"6","key":"2_CR30","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1007\/s10458-019-09422-0","volume":"33","author":"A Morris-Martin","year":"2019","unstructured":"Morris-Martin, A., De Vos, M., Padget, J.: Norm emergence in multiagent systems: a viewpoint paper. Auton. Agents Multi-Agent Syst. 33(6), 706\u2013749 (2019). https:\/\/doi.org\/10.1007\/s10458-019-09422-0","journal-title":"Auton. Agents Multi-Agent Syst."},{"key":"2_CR31","doi-asserted-by":"publisher","first-page":"441","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, pp. 441\u2013470. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-27645-3_14"},{"unstructured":"Perelli, G.: Enforcing equilibria in multi-agent systems. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2019, pp. 188\u2013196. International Foundation for Autonomous Agents and Multiagent Systems, Richland (2019). Event-place: Montreal QC, Canada","key":"2_CR32"},{"issue":"1","key":"2_CR33","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1007\/s10479-010-0688-z","volume":"190","author":"L Relund Nielsen","year":"2011","unstructured":"Relund Nielsen, L., J\u00f8rgensen, E., H\u00f8jsgaard, S.: Embedding a state space model into a Markov decision process. Ann. Oper. Res. 190(1), 289\u2013309 (2011). https:\/\/doi.org\/10.1007\/s10479-010-0688-z","journal-title":"Ann. Oper. Res."},{"unstructured":"Rotolo, A.: Norm compliance of rule-based cognitive agents. In: IJCAI International Joint Conference on Artificial Intelligence, pp. 2716\u20132721, January 2011","key":"2_CR34"},{"key":"2_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1007\/978-3-642-22546-8_6","volume-title":"Rule-Based Reasoning, Programming, and Applications","author":"A Rotolo","year":"2011","unstructured":"Rotolo, A., van der Torre, L.: Rules, agents and norms: guidelines for rule-based normative multi-agent systems. In: Bassiliades, N., Governatori, G., Paschke, A. (eds.) RuleML 2011. LNCS, vol. 6826, pp. 52\u201366. Springer, Heidelberg (2011). https:\/\/doi.org\/10.1007\/978-3-642-22546-8_6"},{"doi-asserted-by":"crossref","unstructured":"Shapley, L.S.: Stochastic games. Proc. Natl. Acad. Sci. U.S.A. 39(10), 1095\u20131100 (1953). https:\/\/pubmed.ncbi.nlm.nih.gov\/16589380","key":"2_CR36","DOI":"10.1073\/pnas.39.10.1953"},{"unstructured":"Shoham, Y., Powers, R., Grenager, T.: Multi-agent reinforcement learning: a critical survey, June 2003","key":"2_CR37"},{"doi-asserted-by":"publisher","unstructured":"Shoham, Y., Tennenholtz, M.: On social laws for artificial agent societies: off-line design. Artif. Intell. 73(1), 231\u2013252 (1995). https:\/\/doi.org\/10.1016\/0004-3702(94)00007-N. http:\/\/www.sciencedirect.com\/science\/article\/pii\/000437029400007N","key":"2_CR38","DOI":"10.1016\/0004-3702(94)00007-N"},{"issue":"2","key":"2_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0056751","volume":"8","author":"WC Stirling","year":"2013","unstructured":"Stirling, W.C., Felin, T.: Game theory, conditional preferences, and social influence. PLOS One 8(2), 1\u201311 (2013). https:\/\/doi.org\/10.1371\/journal.pone.0056751","journal-title":"PLOS One"},{"key":"2_CR40","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)"},{"unstructured":"Watkins, C.: Learning from delayed rewards, January 1989","key":"2_CR41"},{"unstructured":"Wolf, T.D., Holvoet, T.: Emergence and self-organisation: a statement of similarities and differences (2004)","key":"2_CR42"}],"container-title":["Lecture Notes in Computer Science","Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-82254-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T22:49:13Z","timestamp":1672872553000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-82254-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030822538","9783030822545"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-82254-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"20 July 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EUMAS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Multi-Agent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 June 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 June 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eumas2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/biu-ai.com\/EUMAS21\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"16","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.05","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}