{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T04:07:17Z","timestamp":1751861237501,"version":"3.41.0"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T00:00:00Z","timestamp":1658275200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T00:00:00Z","timestamp":1658275200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["1197622N","Onderzoeksprogramma Artifici\u00eble Intelligentie (AI) Vlaanderen"],"award-info":[{"award-number":["1197622N","Onderzoeksprogramma Artifici\u00eble Intelligentie (AI) Vlaanderen"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1007\/s00521-022-07533-6","type":"journal-article","created":{"date-parts":[[2022,7,20]],"date-time":"2022-07-20T07:02:51Z","timestamp":1658300571000},"page":"13119-13144","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Preference communication in multi-objective normal-form games"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5045-6127","authenticated-orcid":false,"given":"Willem","family":"R\u00f6pke","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diederik M.","family":"Roijers","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roxana","family":"R\u0103dulescu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,20]]},"reference":[{"key":"7533_CR1","unstructured":"Anthony, T., Eccles, T., Tacchetti, A., Kram\u00e1r, J., Gemp, I., Hudson, T., Porcel, N., Lanctot, M., Perolat, J., Everett, R., Singh, S., Graepel, T., Bachrach, Y.: Learning to Play No-Press Diplomacy with Best Response Policy Iteration. In: H.\u00a0Larochelle, M.\u00a0Ranzato, R.\u00a0Hadsell, M.F. Balcan, H.\u00a0Lin (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 17987\u201318003. Curran Associates, Inc. (2020). https:\/\/proceedings.neurips.cc\/paper\/2020\/file\/d1419302db9c022ab1d48681b13d5f8b-Paper.pdf"},{"issue":"1","key":"7533_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2140\/pjm.1956.6.1","volume":"6","author":"D Blackwell","year":"1954","unstructured":"Blackwell D (1954) An analog of the minimax theorem for vector payoffs. Pac J Math 6(1):1\u20138. https:\/\/doi.org\/10.2140\/pjm.1956.6.1","journal-title":"Pac J Math"},{"issue":"3","key":"7533_CR3","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1016\/S0377-2217(02)00406-X","volume":"148","author":"P Borm","year":"2003","unstructured":"Borm P, Vermeulen D, Voorneveld M (2003) The structure of the set of equilibria for two person multicriteria games. Eur J Oper Res 148(3):480\u2013493. https:\/\/doi.org\/10.1016\/S0377-2217(02)00406-X","journal-title":"Eur J Oper Res"},{"issue":"2","key":"7533_CR4","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M Bowling","year":"2002","unstructured":"Bowling M, Veloso M (2002) Multiagent learning using a variable learning rate. Artif Intell 136(2):215\u2013250. https:\/\/doi.org\/10.1016\/S0004-3702(02)00121-2","journal-title":"Artif Intell"},{"key":"7533_CR5","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 \u201998\/IAAI \u201998, pp. 746\u2013752. American Association for Artificial Intelligence, Madison, Wisconsin, USA (1998)"},{"issue":"4","key":"7533_CR6","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1007\/BF00942194","volume":"47","author":"HW Corley","year":"1985","unstructured":"Corley HW (1985) Games with vector payoffs. J Optim Theory Appl 47(4):491\u2013498. https:\/\/doi.org\/10.1007\/BF00942194","journal-title":"J Optim Theory Appl"},{"key":"7533_CR7","unstructured":"Foerster, J.N., Assael, Y.M., de\u00a0Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Proceedings of the 30th international conference on neural information processing systems, NIPS\u201916, pp. 2145\u20132153. Curran Associates Inc., Barcelona, Spain (2016)"},{"key":"7533_CR8","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-03098-8_13","volume-title":"PRIMA 2018: principles and practice of multi-agent systems","author":"A Ismaili","year":"2018","unstructured":"Ismaili A (2018) On existence, mixtures, computation and efficiency in multi-objective games. In: Miller T, Oren N, Sakurai Y, Noda I, Savarimuthu BTR, Son TC (eds) PRIMA 2018: principles and practice of multi-agent systems. Springer, Cham, pp 210\u2013225"},{"issue":"1","key":"7533_CR9","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3233\/KES-2010-0206","volume":"15","author":"GJ Laurent","year":"2011","unstructured":"Laurent GJ, Matignon L, Fort-Piat NL (2011) The world of independent learners is not markovian. Int J Knowl Based Intell Eng Syst 15(1):55\u201364. https:\/\/doi.org\/10.3233\/KES-2010-0206","journal-title":"Int J Knowl Based Intell Eng Syst"},{"issue":"2","key":"7533_CR10","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1137\/S0363012903437976","volume":"44","author":"DS Leslie","year":"2005","unstructured":"Leslie DS, Collins EJ (2005) Individual Q-learning in normal form games. SIAM J Control Optim 44(2):495\u2013514. https:\/\/doi.org\/10.1137\/S0363012903437976","journal-title":"SIAM J Control Optim"},{"issue":"6","key":"7533_CR11","doi-asserted-by":"publisher","first-page":"986","DOI":"10.1007\/s10458-013-9246-9","volume":"28","author":"J Letchford","year":"2014","unstructured":"Letchford J, Korzhyk D, Conitzer V (2014) On the value of commitment. Auton Agent Multi-Agent Syst 28(6):986\u20131016. https:\/\/doi.org\/10.1007\/s10458-013-9246-9","journal-title":"Auton Agent Multi-Agent Syst"},{"key":"7533_CR12","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.neucom.2017.05.090","volume":"263","author":"P Mannion","year":"2017","unstructured":"Mannion P, Devlin S, Mason K, Duggan J, Howley E (2017) Policy invariance under reward transformations for multi-objective reinforcement learning. Neurocomputing 263:60\u201373. https:\/\/doi.org\/10.1016\/j.neucom.2017.05.090","journal-title":"Neurocomputing"},{"key":"7533_CR13","first-page":"47","volume-title":"An Experimental review of reinforcement learning algorithms for adaptive traffic signal control","author":"P Mannion","year":"2016","unstructured":"Mannion P, Duggan J, Howley E (2016) An Experimental review of reinforcement learning algorithms for adaptive traffic signal control. Springer, Cham, pp 47\u201366"},{"key":"7533_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2021.105400","volume":"134","author":"N Mazyavkina","year":"2021","unstructured":"Mazyavkina N, Sviridov S, Ivanov S, Burnaev E (2021) Reinforcement learning for combinatorial optimization: a survey. Comput Oper Res 134:105400. https:\/\/doi.org\/10.1016\/j.cor.2021.105400","journal-title":"Comput Oper Res"},{"key":"7533_CR15","unstructured":"Mossalam H, Assael YM, Roijers DM, Whiteson S (2016) Multi-objective deep reinforcement learning"},{"key":"7533_CR16","unstructured":"Noukhovitch M, LaCroix T, Lazaridou A, Courville A (2021) Emergent communication under competition. In: proceedings of the 20th international conference on autonomous agents and multiAgent aystems, AAMAS \u201921, pp. 974\u2013982. International Foundation for Autonomous Agents and Multiagent Systems, Virtual Event, United Kingdom"},{"key":"7533_CR17","doi-asserted-by":"crossref","unstructured":"Now\u00e9 A, Vrancx P, De Hauwere YM (2012) Game theory and multi-agent reinforcement learning. In: Reinforcement learning, pp. 441\u2013470. Springer","DOI":"10.1007\/978-3-642-27645-3_14"},{"issue":"3","key":"7533_CR18","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L Panait","year":"2005","unstructured":"Panait L, Luke S (2005) Cooperative multi-agent learning: the state of the art. Auton Agent Multi-Agent Syst 11(3):387\u2013434. https:\/\/doi.org\/10.1007\/s10458-005-2631-2","journal-title":"Auton Agent Multi-Agent Syst"},{"issue":"1","key":"7533_CR19","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1609\/aimag.v30i1.2173","volume":"30","author":"J Pita","year":"2009","unstructured":"Pita J, Jam M, Ord\u00f3\u00f1ez F, Portway C, Tambe M, Western C, Paruchuri P, Kraus S (2009) Using game theory for los angeles airport security. AI Mag 30(1):43\u201357. https:\/\/doi.org\/10.1609\/aimag.v30i1.2173","journal-title":"AI Mag"},{"key":"7533_CR20","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1613\/jair.3987","volume":"48","author":"DM Roijers","year":"2013","unstructured":"Roijers DM, Vamplew P, Whiteson S, Dazeley R (2013) A survey of multi-objective sequential decision-making. J Artif Intell Res 48:67\u2013113. https:\/\/doi.org\/10.1613\/jair.3987","journal-title":"J Artif Intell Res"},{"key":"7533_CR21","doi-asserted-by":"crossref","unstructured":"Roijers DM, Whiteson S (2017) Multi-objective decision making. In: Synthesis lectures on artificial intelligence and machine learning, vol.\u00a034, p. 129. Morgan and Claypool","DOI":"10.1007\/978-3-031-01576-2"},{"key":"7533_CR22","doi-asserted-by":"crossref","unstructured":"R\u00f6pke W, Radulescu R, Roijers D, Nowe A (2021) Communication strategies in multi-objective normal-form games. In: proceedings of the adaptive and learning agents workshop 2021 (ALA-21)","DOI":"10.1007\/s00521-022-07533-6"},{"key":"7533_CR23","unstructured":"R\u00f6pke W (2021) Communication in multi-objective games. Master\u2019s thesis, Vrije Universiteit Brussel"},{"key":"7533_CR24","doi-asserted-by":"crossref","unstructured":"R\u00f6pke W, Roijers DM, Now\u00e9 A, R\u0103dulescu R (2021) On nash equilibria in normal-form games with vectorial payoffs","DOI":"10.1007\/s10458-022-09582-6"},{"issue":"1","key":"7533_CR25","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1007\/s10458-019-09433-x","volume":"34","author":"R R\u0103dulescu","year":"2020","unstructured":"R\u0103dulescu R, Mannion P, Roijers DM, Now\u00e9 A (2020) Multi-objective multi-agent decision making: a utility-based analysis and survey. Auton Agent Multi-Agent Syst 34(1):10. https:\/\/doi.org\/10.1007\/s10458-019-09433-x","journal-title":"Auton Agent Multi-Agent Syst"},{"key":"7533_CR26","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888920000351","volume":"35","author":"R R\u0103dulescu","year":"2020","unstructured":"R\u0103dulescu R, Mannion P, Zhang Y, Roijers DM, Now\u00e9 A (2020) A utility-based analysis of equilibria in multi-objective normal-form games. Knowl Eng Rev 35:e32. https:\/\/doi.org\/10.1017\/S0269888920000351","journal-title":"Knowl Eng Rev"},{"key":"7533_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06184-3","author":"R R\u0103dulescu","year":"2021","unstructured":"R\u0103dulescu R, Verstraeten T, Zhang Y, Mannion P, Roijers DM, Now\u00e9 A (2021) Opponent learning awareness and modelling in multi-objective normal form games. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-021-06184-3","journal-title":"Neural Comput Appl"},{"issue":"1","key":"7533_CR28","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1002\/nav.3800060107","volume":"6","author":"LS Shapley","year":"1959","unstructured":"Shapley LS, Rigby FD (1959) Equilibrium points in games with vector payoffs. Naval Res Logist Q 6(1):57\u201361. https:\/\/doi.org\/10.1002\/nav.3800060107","journal-title":"Naval Res Logist Q"},{"key":"7533_CR29","unstructured":"Singh S, Kearns M, Mansour Y (2000) Nash convergence of gradient dynamics in general-sum games. In: Proceedings of the sixteenth conference on uncertainty in artificial intelligence, UAI\u201900, pp. 541\u2013548. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA"},{"key":"7533_CR30","doi-asserted-by":"publisher","unstructured":"Sinha A, Fang F, An B, Kiekintveld C, Tambe M (2018) Stackelberg security games: looking beyond a decade of success. In: Proceedings of the twenty-seventh international joint conference on artificial intelligence, IJCAI-18, pp. 5494\u20135501. International Joint Conferences on Artificial Intelligence Organization (2018). https:\/\/doi.org\/10.24963\/ijcai.2018\/775","DOI":"10.24963\/ijcai.2018\/775"},{"key":"7533_CR31","doi-asserted-by":"publisher","unstructured":"Sinha A, Malo P, Frantsev A, Deb K (2013) Multi-objective Stackelberg game between a regulating authority and a mining company: a case study in environmental economics. In: 2013 IEEE congress on evolutionary computation, pp. 478\u2013485. IEEE, Cancun, Mexico. https:\/\/doi.org\/10.1109\/CEC.2013.6557607","DOI":"10.1109\/CEC.2013.6557607"},{"issue":"2","key":"7533_CR32","doi-asserted-by":"publisher","first-page":"446","DOI":"10.1016\/j.geb.2009.11.008","volume":"69","author":"B von Stengel","year":"2010","unstructured":"von Stengel B, Zamir S (2010) Leadership games with convex strategy sets. Games Econom Behav 69(2):446\u2013457. https:\/\/doi.org\/10.1016\/j.geb.2009.11.008","journal-title":"Games Econom Behav"},{"issue":"4","key":"7533_CR33","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"A Tampuu","year":"2017","unstructured":"Tampuu A, Matiisen T, Kodelja D, Kuzovkin I, Korjus K, Aru J, Aru J, Vicente R (2017) Multiagent cooperation and competition with deep reinforcement learning. PLoS ONE 12(4):e0172395. https:\/\/doi.org\/10.1371\/journal.pone.0172395","journal-title":"PLoS ONE"},{"key":"7533_CR34","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1007\/978-3-642-10439-8_35","volume-title":"AI 2009: advances in artificial intelligence","author":"P Vamplew","year":"2009","unstructured":"Vamplew P, Dazeley R, Barker E, Kelarev A (2009) Constructing stochastic mixture policies for episodic multiobjective reinforcement learning tasks. In: Nicholson A, Li X (eds) AI 2009: advances in artificial intelligence. Springer, Berlin Heidelberg, Berlin, Heidelberg, pp 340\u2013349"},{"key":"7533_CR35","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-05859-1","author":"P Vamplew","year":"2021","unstructured":"Vamplew P, Foale C, Dazeley R (2021) The impact of environmental stochasticity on value-based multiobjective reinforcement learning. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-021-05859-1","journal-title":"Neural Comput Appl"},{"key":"7533_CR36","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals O, Babuschkin I, Czarnecki WM, Mathieu M, Dudzik A, Chung J, Choi DH, Powell R, Ewalds T, Georgiev P, Oh J, Horgan D, Kroiss M, Danihelka I, Huang A, Sifre L, Cai T, Agapiou JP, Jaderberg M, Vezhnevets AS, Leblond R, Pohlen T, Dalibard V, Budden D, Sulsky Y, Molloy J, Paine TL, Gulcehre C, Wang Z, Pfaff T, Wu Y, Ring R, Yogatama D, W\u00fcnsch D, McKinney K, Smith O, Schaul T, Lillicrap T, Kavukcuoglu K, Hassabis D, Apps C, Silver D (2019) Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575:350\u2013354. https:\/\/doi.org\/10.1038\/s41586-019-1724-z","journal-title":"Nature"},{"issue":"1","key":"7533_CR37","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s001860000069","volume":"52","author":"M Voorneveld","year":"2000","unstructured":"Voorneveld M, Grahn S, Dufwenberg M (2000) Ideal equilibria in noncooperative multicriteria games. Math Methods Oper Res 52(1):65\u201377. https:\/\/doi.org\/10.1007\/s001860000069","journal-title":"Math Methods Oper Res"},{"key":"7533_CR38","unstructured":"Zhang Y, R\u0103dulescu R, Mannion P, Roijers DM, Now\u00e9 A (2020) Opponent modelling for reinforcement learning in multi-objective normal form games. In: Proceedings of the 19th international conference on autonomous agents and multiAgent systems, AAMAS \u201920, pp. 2080\u20132082. Auckland, New Zealand"},{"key":"7533_CR39","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-47148-x","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Kearnes S, Li L, Zare RN, Riley P (2019) Optimization of molecules via deep reinforcement learning. Sci Rep. https:\/\/doi.org\/10.1038\/s41598-019-47148-x","journal-title":"Sci Rep"},{"key":"7533_CR40","unstructured":"Zinkevich M, Greenwald A, Littman ML (2005) Cyclic equilibria in Markov games. In: Proceedings of the 18th international conference on neural information processing systems, NIPS\u201905, pp. 1641\u20131648. MIT Press, Vancouver, British Columbia, Canada"},{"key":"7533_CR41","unstructured":"Zintgraf LM, Roijers DM, Linders S, Jonker CM, Now\u00e9 A (2018) Ordered preference elicitation strategies for supporting multi-objective decision making. In: Proceedings of the 17th international conference on autonomous agents and multiAgent systems, AAMAS \u201918, pp. 1477\u20131485, Stockholm, Sweden"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07533-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07533-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07533-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T08:27:36Z","timestamp":1751012856000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07533-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,20]]},"references-count":41,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["7533"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07533-6","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2022,7,20]]},"assertion":[{"value":"16 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 June 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 July 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}