{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:27:05Z","timestamp":1759134425444,"version":"3.37.3"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2016,3,28]],"date-time":"2016-03-28T00:00:00Z","timestamp":1459123200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100013165","name":"National Energy Technology Laboratory","doi-asserted-by":"crossref","award":["DE-FE0012302"],"award-info":[{"award-number":["DE-FE0012302"]}],"id":[{"id":"10.13039\/100013165","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2016,10]]},"DOI":"10.1007\/s00500-016-2124-z","type":"journal-article","created":{"date-parts":[[2016,3,28]],"date-time":"2016-03-28T07:52:25Z","timestamp":1459151545000},"page":"3869-3887","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Multi-objective multiagent credit assignment in reinforcement learning and NSGA-II"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3056-9284","authenticated-orcid":false,"given":"Logan","family":"Yliniemi","sequence":"first","affiliation":[]},{"given":"Kagan","family":"Tumer","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,3,28]]},"reference":[{"issue":"8","key":"2124_CR1","doi-asserted-by":"crossref","first-page":"3736","DOI":"10.1016\/j.eswa.2013.11.044","volume":"41","author":"M Agarwal","year":"2014","unstructured":"Agarwal M, Kumar N, Vig L (2014) Non-additive multi-objective robot coalition formation. Exp Syst Appl 41(8):3736\u20133747","journal-title":"Exp Syst Appl"},{"issue":"2","key":"2124_CR2","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1007\/s10458-008-9046-9","volume":"17","author":"AK Agogino","year":"2008","unstructured":"Agogino AK, Tumer K (2008) Analyzing and visualizing multi-agent rewards in dynamic and stochastic domains. J Autonom Agents Multiagent Syst 17(2):320\u2013338","journal-title":"J Autonom Agents Multiagent Syst"},{"key":"2124_CR3","unstructured":"Arthur WB (1984) Inductive reasoning and bounded rationality (the El Farol Problem). Am Econ Rev 84(406):1994"},{"issue":"2","key":"2124_CR4","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1061\/(ASCE)0733-9496(2006)132:2(122)","volume":"132","author":"M Atiquzzaman","year":"2006","unstructured":"Atiquzzaman M, Liong S-Y, Yu X (2006) Alternative decision making in water distribution network with NSGA-II. J Water Res Plann Manag 132(2):122\u2013126","journal-title":"J Water Res Plann Manag"},{"key":"2124_CR5","doi-asserted-by":"crossref","unstructured":"Brys T, Harutyunyan A, Vrancx P, Taylor M, Kudenko D, Nowe A (2014a) Multi-objectivization of reinforcement learning problems by reward shaping. In: 2014 international joint conference on neural networks (IJCNN), pp 2315\u20132322","DOI":"10.1109\/IJCNN.2014.6889732"},{"issue":"1","key":"2124_CR6","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1080\/09540091.2014.885282","volume":"26","author":"T Brys","year":"2014","unstructured":"Brys T, Pham TT, Taylor ME (2014b) Distributed learning and multi-objectivity in traffic light control. Connect Sci 26(1):65\u201383","journal-title":"Connect Sci"},{"key":"2124_CR7","unstructured":"Colby M, Tumer K (2012) Shaping fitness functions for coevolving cooperative multiagent systems. In: Proceedings of the 11th international conference on autonomous agents and multiagent systems. International foundation for autonomous agents and multiagent systems, vol 1, pp 425\u2013432"},{"key":"2124_CR8","doi-asserted-by":"crossref","unstructured":"Colby M, Tumer K (2015) An evolutionary game theoretic analysis of difference evaluation functions. In: Proceedings of the 2015 on genetic and evolutionary computation conference. ACM, New York, pp 1391\u20131398","DOI":"10.1145\/2739480.2754770"},{"key":"2124_CR9","doi-asserted-by":"crossref","unstructured":"Colby M, Chung JJ, Tumer K (2015) Implicit adaptive multi-robot coordination in dynamic environments. In: 2015 IEEE\/RSJ international conference on intelligent robots and systems (IROS). IEEE, New York, pp 5168\u20135173","DOI":"10.1109\/IROS.2015.7354105"},{"key":"2124_CR10","doi-asserted-by":"crossref","unstructured":"Colby M, Yliniemi L, Tumer K (2016) Autonomous multiagent space exploration with high-level human feedback. J Aerospace Inf Syst (to appear)","DOI":"10.2514\/1.I010379"},{"key":"2124_CR11","doi-asserted-by":"crossref","unstructured":"Damiani S, Verfaillie G, Charmeau MC (2005) An earth watching satellite constellation: how to manage a team of watching agents with limited communications. Autonom Agents Multiagent Syst","DOI":"10.1145\/1082473.1082543"},{"key":"2124_CR12","doi-asserted-by":"crossref","unstructured":"Das I, Dennis JE (1997) A closer look at drawbacks of minimizing weighted sums of objectives for pareto set generation in multicriteria optimization problems. Struct Optim, 63\u201369","DOI":"10.1007\/BF01197559"},{"key":"2124_CR13","doi-asserted-by":"crossref","unstructured":"Deb K, Pratap A, Moitra S (2000) Mechanical component design for multiple ojectives using elitist non-dominated sorting ga. In: Parallel problem solving from nature PPSN VI. Springer, Berlin, pp 859\u2013868","DOI":"10.1007\/3-540-45356-3_84"},{"key":"2124_CR14","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1109\/4235.996017","volume":"6","author":"K Deb","year":"2002","unstructured":"Deb K, Pratap A, Agarwal S, Meyarivan T (2002) A fast elitist multi-objective genetic algorithm: NSGA-II. Evol Comput 6:182\u2013197","journal-title":"Evol Comput"},{"key":"2124_CR15","unstructured":"Devlin S, Yliniemi L, Kudenko D, Tumer K (2014) Potential-based difference rewards for multiagent reinforcement learning. In: Proceedings of the 2014 international conference on autonomous agents and multi-agent systems, AAMAS \u201914, 2014, pp 165\u2013172. ISBN 978-1-4503-2738-1"},{"key":"2124_CR16","doi-asserted-by":"crossref","unstructured":"Dresner K, Stone P (2008) A multiagent approach to autonomous intersection management. J Artif Intell Res 591\u2013656","DOI":"10.1613\/jair.2502"},{"key":"2124_CR17","doi-asserted-by":"crossref","unstructured":"Dusparic I, Cahill V (2009) Distributed w-learning: multi-policy optimization in self-organizing systems. In: Third IEEE international conference on self-adaptive and self-organizing systems, 2009. SASO\u201909. IEEE, New York, pp 20\u201329","DOI":"10.1109\/SASO.2009.23"},{"key":"2124_CR18","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1007\/3-540-61723-X_1022","volume":"1141","author":"CM Fonseca","year":"1996","unstructured":"Fonseca CM, Fleming PJ (1996) On the performance assessment and comparison of stochastic multiobjective optimizers. Lect Notes Comput Sci 1141:584\u2013593","journal-title":"Lect Notes Comput Sci"},{"key":"2124_CR19","doi-asserted-by":"crossref","unstructured":"Fonseca CM, Guerreiro AP, Lopez-Ibanez M, Paquete L (2011) On the computation of the empirical attainment function. LNCS 6576:121\u2013135","DOI":"10.1007\/978-3-642-19893-9_8"},{"key":"2124_CR20","unstructured":"G\u00e1bor Z, Kalm\u00e1r Z, Szepesv\u00e1ri C (1998) Multi-criteria reinforcement learning. ICML 98:197\u2013205"},{"key":"2124_CR21","first-page":"61801","volume":"51","author":"DE Goldberg","year":"1991","unstructured":"Goldberg DE, Deb K (1991) A comparative analysis of selection schemes used in genetic algorithms. Urbana 51:61801\u20132996","journal-title":"Urbana"},{"issue":"6","key":"2124_CR22","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1109\/TBME.2011.2110651","volume":"58","author":"SMK Heris","year":"2011","unstructured":"Heris SMK, Khaloozadeh H (2011) Open-and closed-loop multiobjective optimal strategies for HIV therapy using NSGA-II. IEEE Trans Biomed Eng 58(6):1678\u20131685","journal-title":"IEEE Trans Biomed Eng"},{"issue":"5","key":"2124_CR23","doi-asserted-by":"crossref","first-page":"3638","DOI":"10.1016\/j.eswa.2009.10.027","volume":"37","author":"B Huang","year":"2010","unstructured":"Huang B, Buckley B, Kechadi T-M (2010) Multi-objective feature selection by using NSGA-II for customer churn prediction in telecommunications. Exp Syst Appl 37(5):3638\u20133646","journal-title":"Exp Syst Appl"},{"issue":"2","key":"2124_CR24","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.ijepes.2010.08.017","volume":"33","author":"S Jeyadevi","year":"2011","unstructured":"Jeyadevi S, Baskar S, Babulal C, Willjuice MI (2011) Solving multiobjective optimal reactive power dispatch using modified NSGA-II. Int J Electrical Power Energy Syst 33(2):219\u2013228","journal-title":"Int J Electrical Power Energy Syst"},{"key":"2124_CR25","doi-asserted-by":"crossref","unstructured":"Kaelbling LP, Littman ML, Moore AW (1996) Reinforcement learning: a survey. J Artif Intell Res","DOI":"10.1613\/jair.301"},{"key":"2124_CR26","doi-asserted-by":"crossref","unstructured":"Khu ST, Madsen H (2005) Multiobjective calibration with pareto preference ordering: An application to rainfall-runoff model calibration. Water Resour Res 41(3)","DOI":"10.1029\/2004WR003041"},{"key":"2124_CR27","doi-asserted-by":"crossref","unstructured":"Knudson M, Tumer K (2010) Coevolution of heterogeneous multi-robot teams. In: Proceedings of the 12th annual conference on genetic and evolutionary computation","DOI":"10.1145\/1830483.1830506"},{"key":"2124_CR28","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1007\/s00158-003-0368-6","volume":"26","author":"R Marler","year":"2004","unstructured":"Marler R, Arora JS (2004) Survey of multi-objective optimization methods for engineering. Struct Multidiscipl Optim 26:369\u2013395","journal-title":"Struct Multidiscipl Optim"},{"key":"2124_CR29","doi-asserted-by":"crossref","unstructured":"Nandasana AD, Ray AK, Gupta SK (2003) Applications of the non-dominated sorting genetic algorithm (NSGA) in chemical reaction engineering. Int J Chem Reactor Eng 1","DOI":"10.2202\/1542-6580.1018"},{"issue":"4","key":"2124_CR30","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1162\/EVCO_a_00004","volume":"18","author":"L Panait","year":"2010","unstructured":"Panait L (2010) Theoretical convergence guarantees for cooperative coevolutionary algorithms. Evol Comput 18(4):581\u2013615","journal-title":"Evol Comput"},{"key":"2124_CR31","doi-asserted-by":"crossref","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. J Auton Agents Multi-Agent Syst 11:387\u2013434","journal-title":"J Auton Agents Multi-Agent Syst"},{"key":"2124_CR32","unstructured":"Pareto V (1927) Manual of political economy. MacMillan Press Ltd., London"},{"key":"2124_CR33","doi-asserted-by":"crossref","unstructured":"Parsopoulos K, Vrahatis MN (2002) Particle swarm optimization method in multiobjective problems. In: ACM symposium on applied computing","DOI":"10.1145\/508791.508907"},{"key":"2124_CR34","unstructured":"Proper S, Tumer K (2012) Modeling difference rewards for multiagent learning. In: Proceedings of the 11th international conference on autonomous agents and multiagent systems. International foundation for autonomous agents and multiagent systems, vol 3, pp 1397\u20131398"},{"key":"2124_CR35","doi-asserted-by":"crossref","unstructured":"Rajagopalan P, Rawal A, Miikkulainen R (2010) Emergence of competitive and cooperative behavior using coevolution. GECCO, pp 1073\u20131074","DOI":"10.1145\/1830483.1830681"},{"issue":"2","key":"2124_CR36","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1016\/j.asoc.2011.09.015","volume":"12","author":"S Ramesh","year":"2012","unstructured":"Ramesh S, Kannan S, Baskar S (2012) Application of modified NSGA-II algorithm to multi-objective reactive power planning. Appl Soft Comput 12(2):741\u2013753","journal-title":"Appl Soft Comput"},{"key":"2124_CR37","doi-asserted-by":"crossref","unstructured":"Rebhuhn C, Gilchrist B, Oman S, Tumer I, Stone R, Tumer K (2014) A multiagent approach to evaluating innovative component selection. In: Gero JS (ed) Design, computing, and cognition","DOI":"10.1007\/978-3-319-14956-1_13"},{"issue":"2","key":"2124_CR38","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1061\/(ASCE)0887-3801(2007)21:2(136)","volume":"21","author":"MJ Reddy","year":"2007","unstructured":"Reddy MJ, Kumar DN (2007) Multiobjective differential evolution with application to reservoir system optimization. J Comput Civil Eng 21(2):136\u2013146","journal-title":"J Comput Civil Eng"},{"key":"2124_CR39","doi-asserted-by":"crossref","unstructured":"Roijers DM, Vamplew P, Whiteson S, Dazeley R (2013a) A survey of multi-objective sequential decision-making. J Artif Intell Res","DOI":"10.1613\/jair.3987"},{"key":"2124_CR40","unstructured":"Roijers DM, Whiteson S, Oliehoek FA (2013b) Multi-objective variable elimination for collaborative graphical games. In: Proceedings of the 2013 international conference on autonomous agents and multi-agent systems, AAMAS \u201913, pp 1209\u20131210. ISBN 978-1-4503-1993-5"},{"key":"2124_CR41","unstructured":"Roijers DM, Whiteson S, Oliehoek FA (2014) Linear support for multi-objective coordination graphs. In: Proceedings of the 2014 international conference on autonomous agents and multi-agent systems. In: International foundation for autonomous agents and multiagent systems, pp 1297\u20131304"},{"key":"2124_CR42","unstructured":"Rosehart W, Ca\u00f1izares CA, Quintana VH (2001) Multi-objective optimal power flows to evaluate voltage security costs in power networks. IEEE Tr Power Syst"},{"key":"2124_CR43","unstructured":"Rubenstein M, Cabrera A, Werfel J, Habibi G, McLurkin J, Nagpal R (2013) Collective transport of complex objects by simple robots: theory and experiments. AAMAS, Bologna"},{"issue":"3","key":"2124_CR44","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1023\/A:1007678930559","volume":"38","author":"S Singh","year":"2000","unstructured":"Singh S, Jaakkola T, Littman ML, Szepesv\u00e1ri C (2000) Convergence results for single-step on-policy reinforcement-learning algorithms. Mach Learn 38(3):287\u2013308","journal-title":"Mach Learn"},{"key":"2124_CR45","doi-asserted-by":"crossref","unstructured":"Soyel H, Tekguc U, Demirel H (2011) Application of NSGA-II to feature selection for facial expression recognition. Comput Electrical Eng 37(6)","DOI":"10.1016\/j.compeleceng.2011.01.010"},{"key":"2124_CR46","doi-asserted-by":"crossref","unstructured":"Sutton R, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge","DOI":"10.1016\/S1474-6670(17)38315-5"},{"key":"2124_CR47","doi-asserted-by":"crossref","unstructured":"Taylor A, Dusparic I, Galv\u00e1n-L\u00f3pez E, Clarke S, Cahill V (2014) Accelerating learning in multi-objective systems through transfer learning. In: 2014 international joint conference on neural networks (IJCNN). IEEE, New York, pp 2298\u20132305","DOI":"10.1109\/IJCNN.2014.6889438"},{"key":"2124_CR48","doi-asserted-by":"crossref","unstructured":"Tomlin C, Pappas GJ, Sastry S (1998) Conflict resolution for air traffic management: a study in multiagent hybrid systems. IEEE Trans Autom Control 43(4):509\u2013521","DOI":"10.1109\/9.664154"},{"key":"2124_CR49","unstructured":"Tumer K (2005) Designing agent utilities for coordinated, scalable and robust multi-agent systems. In: Scerri P, Mailler R, Vincent R (eds) Challenges in the coordination of large scale multiagent systems. Springer, Berlin"},{"key":"2124_CR50","doi-asserted-by":"crossref","first-page":"493","DOI":"10.1142\/S0219525909002283","volume":"12","author":"K Tumer","year":"2009","unstructured":"Tumer K, Agogino A (2009) Multiagent learning for black box system reward functions. Adv Complex Syst 12:493\u2013512","journal-title":"Adv Complex Syst"},{"volume-title":"Collectives and the design of complex systems","year":"2004","key":"2124_CR51","unstructured":"Tumer K, Wolpert D (eds) (2004a) Collectives and the design of complex systems. Springer, New York"},{"key":"2124_CR52","doi-asserted-by":"crossref","unstructured":"Tumer K, Wolpert D (2004b) A survey of collectives. In: Collectives and the design of complex systems. Springer, Berlin, pp 1\u201342","DOI":"10.1007\/978-1-4419-8909-3_1"},{"key":"2124_CR53","doi-asserted-by":"crossref","unstructured":"Tumer, K, Agogino A, Wolpert D (2002) Learning sequences of actions in collectives of autonomous agents. In: AAMAS, Bologna, pp 378\u2013385","DOI":"10.1145\/544741.544832"},{"key":"2124_CR54","doi-asserted-by":"crossref","unstructured":"Vamplew P, Dazeley R, Berry A, Issabekov R, Dekker E (2010) Empirical evaluation methods for multiobjective reinforcement learning algorithms. Mach Learn","DOI":"10.1007\/s10994-010-5232-5"},{"key":"2124_CR55","unstructured":"Vasirani M, Ossowski S (2009) A market-inspired approach to reservation-based urban road traffic management. In: Proceedings of the 8th international conference on autonomous agents and multiagent systems"},{"key":"2124_CR56","doi-asserted-by":"crossref","unstructured":"Veldhuizen DAV (1999) Multiobjective evolutionary algorithms: classifications analyses and new innovations. PhD thesis, Air Force Institute of Technology","DOI":"10.1145\/298151.298382"},{"issue":"2","key":"2124_CR57","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1162\/106365600568158","volume":"8","author":"DAV Veldhuizen","year":"2000","unstructured":"Veldhuizen DAV, Lamont GB (2000) Multiobjective evolutionary algorithms: analyzing the state-of-the-art. Evol Comput 8(2):125\u2013147","journal-title":"Evol Comput"},{"issue":"3\/4","key":"2124_CR58","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1023\/A:1022676722315","volume":"8","author":"C Watkins","year":"1992","unstructured":"Watkins C, Dayan P (1992) Q-learning. Mach Learn 8(3\/4):279\u2013292","journal-title":"Mach Learn"},{"issue":"2\/3","key":"2124_CR59","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1142\/S0219525901000188","volume":"4","author":"DH Wolpert","year":"2001","unstructured":"Wolpert DH, Tumer K (2001) Optimal payoff functions for members of collectives. Adv Complex Syst 4(2\/3):265\u2013279","journal-title":"Adv Complex Syst"},{"key":"2124_CR60","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1613\/jair.995","volume":"16","author":"DH Wolpert","year":"2002","unstructured":"Wolpert DH, Tumer K (2002) Collective intelligence, data routing and braess\u2019 paradox. J Artif Intell Res 16:359\u2013387","journal-title":"J Artif Intell Res"},{"key":"2124_CR61","doi-asserted-by":"crossref","unstructured":"Wolpert DH, Wheeler K, Tumer K (2000) Collective intelligence for control of distributed dynamical systems. Europhys Lett 49(6)","DOI":"10.1209\/epl\/i2000-00208-x"},{"key":"2124_CR62","doi-asserted-by":"crossref","first-page":"017701","DOI":"10.1103\/PhysRevE.69.017701","volume":"69","author":"DH Wolpert","year":"2004","unstructured":"Wolpert DH, Tumer K, Bandari E (2004) Improving search algorithms by using intelligent coordinates. Phys Rev E 69:017701","journal-title":"Phys Rev E"},{"key":"2124_CR63","unstructured":"Wooldridge M (2002) An introduction to multiagent systems. Wiley, New York"},{"key":"2124_CR64","unstructured":"Zitzler E, Laumanns M, Thiele L (2002) SPEA2: improving the strength pareto evolutionary algorithm for multiobjective optimization. In: Evolutionary methods for design, optimisation, and control, pp 19\u201326"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-016-2124-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00500-016-2124-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-016-2124-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-016-2124-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,16]],"date-time":"2020-05-16T17:15:12Z","timestamp":1589649312000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00500-016-2124-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3,28]]},"references-count":64,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2016,10]]}},"alternative-id":["2124"],"URL":"https:\/\/doi.org\/10.1007\/s00500-016-2124-z","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"type":"print","value":"1432-7643"},{"type":"electronic","value":"1433-7479"}],"subject":[],"published":{"date-parts":[[2016,3,28]]}}}