{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:39:53Z","timestamp":1775579993928,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642371394","type":"print"},{"value":"9783642371400","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-37140-0_28","type":"book-chapter","created":{"date-parts":[[2013,3,12]],"date-time":"2013-03-12T15:18:19Z","timestamp":1363101499000},"page":"352-366","source":"Crossref","is-referenced-by-count":42,"title":["Hypervolume-Based Multi-Objective Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Kristof","family":"Van Moffaert","sequence":"first","affiliation":[]},{"given":"Madalina M.","family":"Drugan","sequence":"additional","affiliation":[]},{"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"2","key":"28_CR1","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1109\/4235.996017","volume":"6","author":"K.D. Deb","year":"2002","unstructured":"Deb, K.D., Pratap, A., Agarwal, S., Meyarivan, T.: A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Transactions on Evolutionary Computation\u00a06(2), 182\u2013197 (2002)","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"28_CR2","unstructured":"Lizotte, D.J., Bowling, M., Murphy, S.A.: Efficient reinforcement learning with multiple reward functions for randomized controlled trial analysis. In: Proceedings of the Twenty-Seventh International Conference on Machine Learning (ICML), pp. 695\u2013702 (2010)"},{"key":"28_CR3","unstructured":"G\u00e1bor, Z., Kalm\u00e1r, Z., Szepesv\u00e1ri, C.: Multi-criteria reinforcement learning. In: Shavlik, J.W. (ed.) ICML, pp. 197\u2013205. Morgan Kaufmann (1998)"},{"key":"28_CR4","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1145\/1390156.1390162","volume-title":"Proceedings of the 25th International Conference on Machine Learning, ICML 2008","author":"L. Barrett","year":"2008","unstructured":"Barrett, L., Narayanan, S.: Learning all optimal policies with multiple criteria. In: Proceedings of the 25th International Conference on Machine Learning, ICML 2008, pp. 41\u201347. ACM, New York (2008)"},{"key":"28_CR5","series-title":"International Series in Operations Research and Management Science","volume-title":"Nonlinear Multiobjective Optimization","author":"K. Miettinen","year":"1999","unstructured":"Miettinen, K.: Nonlinear Multiobjective Optimization. International Series in Operations Research and Management Science, vol.\u00a012. Kluwer Academic Publishers, Dordrecht (1999)"},{"issue":"6-7","key":"28_CR6","doi-asserted-by":"publisher","first-page":"601","DOI":"10.1016\/j.comgeo.2010.03.004","volume":"43","author":"K. Bringmann","year":"2010","unstructured":"Bringmann, K., Friedrich, T.: Approximating the volume of unions and intersections of high-dimensional geometric objects. Comput. Geom. Theory Appl.\u00a043(6-7), 601\u2013610 (2010)","journal-title":"Comput. Geom. Theory Appl."},{"issue":"1","key":"28_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1162\/evco.2007.15.1.1","volume":"15","author":"C. Igel","year":"2007","unstructured":"Igel, C., Hansen, N., Roth, S.: Covariance matrix adaptation for multi-objective optimization. Evol. Comput.\u00a015(1), 1\u201328 (2007)","journal-title":"Evol. Comput."},{"issue":"3","key":"28_CR8","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1016\/j.ejor.2006.08.008","volume":"181","author":"N. Beume","year":"2007","unstructured":"Beume, N., Naujoks, B., Emmerich, M.: Sms-emoa: Multiobjective selection based on dominated hypervolume. European Journal of Operational Research\u00a0181(3), 1653\u20131669 (2007)","journal-title":"European Journal of Operational Research"},{"key":"28_CR9","unstructured":"Watkins, C.: Learning from Delayed Rewards. PhD thesis, University of Cambridge,England (1989)"},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Wiering, M.A., de Jong, E.D.: Computing Optimal Stationary Policies for Multi-Objective Markov Decision Processes. In: 2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning, pp. 158\u2013165. IEEE (April 2007)","DOI":"10.1109\/ADPRL.2007.368183"},{"key":"28_CR11","doi-asserted-by":"crossref","unstructured":"Van Moffaert, K., M. Drugan, M., Now\u00e9, A.: Multi-objective reinforcement learning using scalarization functions. Technical report, Computational Modeling Lab, Vrije Universiteit Brussel, Brussels, Belgium (2012)","DOI":"10.1007\/978-3-642-37140-0_28"},{"issue":"1-2","key":"28_CR12","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s10994-010-5232-5","volume":"84","author":"P. Vamplew","year":"2010","unstructured":"Vamplew, P., Dazeley, R., Berry, A., Issabekov, R., Dekker, E.: Empirical evaluation methods for multiobjective reinforcement learning algorithms. Machine Learning\u00a084(1-2), 51\u201380 (2010)","journal-title":"Machine Learning"},{"key":"28_CR13","unstructured":"Gibbons, J., Chakraborti, S.: Nonparametric Statistical Inference. Statistics, Textbooks and monographs. Marcel Dekker (2003)"},{"key":"28_CR14","doi-asserted-by":"crossref","unstructured":"Veldhuizen, D.A.V., Lamont, G.B.: Multiobjective evolutionary algorithm research: A history and analysis (1998)","DOI":"10.1145\/298151.298382"},{"key":"28_CR15","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1145\/1830483.1830569","volume-title":"Proceedings of the 12th Annual Conference On Genetic and Evolutionary Computation, GECCO 2010","author":"T. Ulrich","year":"2010","unstructured":"Ulrich, T., Bader, J., Zitzler, E.: Integrating decision space diversity into hypervolume-based multiobjective search. In: Proceedings of the 12th Annual Conference On Genetic and Evolutionary Computation, GECCO 2010, pp. 455\u2013462. ACM, New York (2010)"}],"container-title":["Lecture Notes in Computer Science","Evolutionary Multi-Criterion Optimization"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-37140-0_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,11]],"date-time":"2022-02-11T05:04:04Z","timestamp":1644555844000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-37140-0_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642371394","9783642371400"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-37140-0_28","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013]]}}}