{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T10:50:20Z","timestamp":1783075820104,"version":"3.54.6"},"publisher-location":"Berlin, Heidelberg","reference-count":40,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642306709","type":"print"},{"value":"9783642306716","type":"electronic"}],"license":[{"start":{"date-parts":[[2013,1,1]],"date-time":"2013-01-01T00:00:00Z","timestamp":1356998400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-30671-6_17","type":"book-chapter","created":{"date-parts":[[2012,7,31]],"date-time":"2012-07-31T09:07:24Z","timestamp":1343725644000},"page":"433-452","source":"Crossref","is-referenced-by-count":22,"title":["Boosting Metaheuristic Search Using Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Tony","family":"Wauters","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katja","family":"Verbeeck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Patrick","family":"De Causmaecker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Greet","family":"Vanden Berghe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Bai, R., Burke, E.K., Gendreau, M., Kendall, G., Mccollum, B.: Memory length in hyper-heuristics: An empirical study. In: Proceedings of the 2007 IEEE Symposium on Computational Intelligence in Scheduling, CI-Sched 2007 (2007)","DOI":"10.1109\/SCIS.2007.367686"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Battiti, R., Brunato, M., Mascia, F.: Reactive Search and Intelligent Optimization. Operations research\/Computer Science Interfaces, vol.\u00a045. Springer (2008)","DOI":"10.1007\/978-0-387-09624-7"},{"key":"17_CR3","first-page":"1265","volume":"7","author":"K.P. Bennett","year":"2006","unstructured":"Bennett, K.P., Parrado-Hern\u00e1ndez, E.: The interplay of optimization and machine learning research. J. Mach. Learn. Res.\u00a07, 1265\u20131281 (2006)","journal-title":"J. Mach. Learn. Res."},{"key":"17_CR4","unstructured":"Boyan, J.: Learning Evaluation Functions for Global Optimization. PhD thesis, Carnegie-Mellon University (1998)"},{"key":"17_CR5","first-page":"2000","volume":"1, 2000","author":"J. Boyan","year":"2000","unstructured":"Boyan, J., Moore, A.W., Kaelbling, P.: Learning evaluation functions to improve optimization by local search. Journal of Machine Learning Research\u00a01, 2000 (2000)","journal-title":"Journal of Machine Learning Research"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Burke, E., Hart, E., Kendall, G., Newall, J., Ross, P., Schulenburg, S.: Hyper-heuristics: An emerging direction in modern search technology. In: Handbook of Metaheuristics, pp. 457\u2013474. Kluwer Academic Publishers (2003)","DOI":"10.1007\/0-306-48056-5_16"},{"key":"17_CR7","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1023\/B:HEUR.0000012446.94732.b6","volume":"9","author":"E.K. Burke","year":"2003","unstructured":"Burke, E.K., Kendall, G., Soubeiga, E.: A tabu-search hyperheuristic for timetabling and rostering. Journal of Heuristics\u00a09, 451\u2013470 (2003)","journal-title":"Journal of Heuristics"},{"key":"17_CR8","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1016\/j.cor.2011.01.007","volume":"38","author":"S. Ceschia","year":"2011","unstructured":"Ceschia, S., Schaerf, A.: Local search and lower bounds for the patient admission scheduling problem. Computers & Operartions Research\u00a038, 1452\u20131463 (2011)","journal-title":"Computers & Operartions Research"},{"key":"17_CR9","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s10479-006-0158-9","volume":"150","author":"G. Confessore","year":"2007","unstructured":"Confessore, G., Giordani, S., Rismondo, S.: A market-based multi-agent system model for decentralized multi-project scheduling. Annals of Operational Research\u00a0150, 115\u2013135 (2007)","journal-title":"Annals of Operational Research"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Demaine, E.D., Demaine, M.L.: Jigsaw puzzles, edge matching, and polyomino packing: Connections and complexity. Graphs and Combinatorics\u00a023, 195\u2013208 (2007); Special issue on Computational Geometry and Graph Theory: The Akiyama-Chvatal Festschrift","DOI":"10.1007\/s00373-007-0713-4"},{"key":"17_CR11","unstructured":"Demeester. P.: Patient admission scheduling website (2009), \n                      http:\/\/allserv.kahosl.be\/~peter\/pas\/\n                     (last visit August 15, 2011)"},{"key":"17_CR12","unstructured":"Demeester, P., De Causmaecker, P., Vanden Berghe, G.: Applying a local search algorithm to automatically assign patients to beds. In: Proceedings of the 22nd Conference on Quantitive Decision Making (Orbel 22), pp. 35\u201336 (2008)"},{"key":"17_CR13","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.artmed.2009.09.001","volume":"48","author":"P. Demeester","year":"2010","unstructured":"Demeester, P., Souffriau, W., De Causmaecker, P., Vanden Berghe, G.: A hybrid tabu search algorithm for automatically assigning patients to beds. Artif. Intell. Med.\u00a048, 61\u201370 (2010)","journal-title":"Artif. Intell. Med."},{"key":"17_CR14","unstructured":"Dietterich, T.G., Zhang, W.: Solving combinatorial optimization tasks by reinforcement learning: A general methodology applied to resource-constrained scheduling. Journal of Artificial Intelligence Research (2000)"},{"key":"17_CR15","unstructured":"Gabel, T.: Multi-agent Reinforcement Learning Approaches for Distributed Job-Shop Scheduling Problems. PhD thesis, Universit\u00e4t Osnabr\u00fcck, Deutschland (2009)"},{"key":"17_CR16","doi-asserted-by":"crossref","unstructured":"Gambardella, L.M., Dorigo, M.: Ant-q: A r\u00e9inforcement learning approach to the traveling salesman problem, pp. 252\u2013260. Morgan Kaufmann (1995)","DOI":"10.1016\/B978-1-55860-377-6.50039-6"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Glover, F., Kochenberger, G.A.: Handbook of metaheuristics. Springer (2003)","DOI":"10.1007\/b101874"},{"key":"17_CR18","doi-asserted-by":"crossref","unstructured":"Homberger, J.: A (\u03bc, \u03bb)-coordination mechanism for agent-based multi-project scheduling. OR Spectrum (2009), doi:10.1007\/s00291-009-0178-3","DOI":"10.1007\/s00291-009-0178-3"},{"key":"17_CR19","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","volume":"4","author":"L.P. Kaelbling","year":"1996","unstructured":"Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: A survey. Journal of Artificial Intelligence Research\u00a04, 237\u2013285 (1996)","journal-title":"Journal of Artificial Intelligence Research"},{"key":"17_CR20","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 Machine Learning, pp. 157\u2013163. Morgan Kaufmann (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"17_CR21","unstructured":"Miagkikh, V.V., Punch III, W.F.: An approach to solving combinatorial optimization problems using a population of reinforcement learning agents (1999)"},{"key":"17_CR22","unstructured":"Misir, M., Wauters, T., Verbeeck, K., Vanden Berghe, G.: A new learning hyper-heuristic for the traveling tournament problem. In: Proceedings of Metaheuristic International Conference (2009)"},{"key":"17_CR23","unstructured":"Moll, R., Barto, A.G., Perkins, T.J., Sutton, R.S.: Learning instance-independent value functions to enhance local search. In: Advances in Neural Information Processing Systems, pp. 1017\u20131023. MIT Press (1998)"},{"key":"17_CR24","unstructured":"Narendra, K., Thathachar, M.: Learning Automata: An Introduction. Prentice-Hall International, Inc. (1989)"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Nareyek, A.: Choosing search heuristics by non-stationary reinforcement learning. In: Metaheuristics: Computer Decision-Making, pp. 523\u2013544. Kluwer Academic Publishers (2001)","DOI":"10.1007\/978-1-4757-4137-7_25"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"\u00d6zcan, E., Misir, M., Ochoa, G., Burke, E.K.: A reinforcement learning - great-deluge hyper-heuristic for examination timetabling. Int. J. of Applied Metaheuristic Computing, 39\u201359 (2010)","DOI":"10.4018\/jamc.2010102603"},{"key":"17_CR27","unstructured":"Rummery, G.A., Niranjan, M.: On-line q-learning using connectionist systems. Technical Report CUED\/F-INFENG\/TR 166, Engineering Department, Cambridge University (1994)"},{"key":"17_CR28","first-page":"1038","volume-title":"Advances in Neural Information Processing Systems: Proceedings of the 1995 Conference","author":"S. Richard","year":"1996","unstructured":"Richard, S., Sutton, R.S.: Generalization in reinforcement learning: Successful examples using sparse coarse coding. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems: Proceedings of the 1995 Conference, pp. 1038\u20131044. MIT Press, Cambridge (1996)"},{"key":"17_CR29","doi-asserted-by":"crossref","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: an introduction. MIT Press (1998)","DOI":"10.1109\/TNN.1998.712192"},{"key":"17_CR30","doi-asserted-by":"crossref","unstructured":"Talbi, E.-G.: Metaheuristics: From Design to Implementation. John Wiley and Sons (2009)","DOI":"10.1002\/9780470496916"},{"key":"17_CR31","first-page":"1633","volume":"10","author":"M.E. Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: A survey. J. Mach. Learn. Res.\u00a010, 1633\u20131685 (2009)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"17_CR32","first-page":"2125","volume":"8","author":"M.E. Taylor","year":"2007","unstructured":"Taylor, M.E., Stone, P., Liu, Y.: Transfer learning via inter-task mappings for temporal difference learning. Journal of Machine Learning Research\u00a08(1), 2125\u20132167 (2007)","journal-title":"Journal of Machine Learning Research"},{"key":"17_CR33","doi-asserted-by":"crossref","unstructured":"Thathachar, M.A.L., Sastry, P.S.: Networks of Learning Automata: Techniques for Online Stochastic Optimization. Kluwer Academic Publishers (2004)","DOI":"10.1007\/978-1-4419-9052-5"},{"key":"17_CR34","first-page":"279","volume":"8","author":"C.J.C.H. Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"},{"key":"17_CR35","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. PhD thesis, Cambridge University (1989)"},{"key":"17_CR36","unstructured":"Wauters, T., Verbeeck, K., De Causmaecker, P., Vanden Berghe, G.: A game theoretic approach to decentralized multi-project scheduling (extended abstract). In: Proc. of 9th Int. Conf. on Autonomous Agents and Multiagent Systems, AAMAS 2010, vol.\u00a0R24 (2010)"},{"issue":"2","key":"17_CR37","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1057\/jors.2010.101","volume":"62","author":"T. Wauters","year":"2011","unstructured":"Wauters, T., Verbeeck, K., Vanden Berghe, G., De Causmaecker, P.: Learning agents for the multi-mode project scheduling problem. Journal of the Operational Research Society\u00a062(2), 281\u2013290 (2011)","journal-title":"Journal of the Operational Research Society"},{"key":"17_CR38","unstructured":"Wauters, T., Verstichel, J., Verbeeck, K., Vanden Berghe, G.: A learning metaheuristic for the multi mode resource constrained project scheduling problem. In: Proceedings of the Third Learning and Intelligent OptimizatioN Conference, LION3 (2009)"},{"key":"17_CR39","doi-asserted-by":"crossref","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 229\u2013256 (1992)","DOI":"10.1007\/BF00992696"},{"key":"17_CR40","unstructured":"Zhang, W., Dietterich, T.: A reinforcement learning approach to job-shop scheduling. In: Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, pp. 1114\u20131120. Morgan Kaufmann (1995)"}],"container-title":["Studies in Computational Intelligence","Hybrid Metaheuristics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-30671-6_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T09:16:06Z","timestamp":1675934166000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-642-30671-6_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642306709","9783642306716"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-30671-6_17","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"value":"1860-949X","type":"print"},{"value":"1860-9503","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013]]}}}