{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T04:13:16Z","timestamp":1750306396148,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2015,7,11]],"date-time":"2015-07-11T00:00:00Z","timestamp":1436572800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003130","name":"Fonds Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["FWOAL726"],"award-info":[{"award-number":["FWOAL726"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,7,11]]},"DOI":"10.1145\/2739482.2756582","type":"proceedings-article","created":{"date-parts":[[2015,7,10]],"date-time":"2015-07-10T14:10:55Z","timestamp":1436537455000},"page":"723-740","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Synergies between Evolutionary Algorithms and Reinforcement Learning"],"prefix":"10.1145","author":[{"given":"Madalina M.","family":"Drugan","sequence":"first","affiliation":[{"name":"Vrije Universiteit Brussel, Brussels, Belgium"}]}],"member":"320","published-online":{"date-parts":[[2015,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-27645-3","volume-title":"Martijn van Otterlo: Reinforcement Learning: State-of-the-Art","author":"Wiering Marco A.","year":"2012"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_4_1","first-page":"101","article-title":"The QV family compared to other reinforcement learning algorithms","volume":"2009","author":"Wiering Marco A.","journal-title":"ADPRL"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000024"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"David E. Moriarty Alan C. Schultz John J. Grefenstette: Evolutionary Algorithms for Reinforcement Learning. J. Artif. Intell. Res. (JAIR) 11: 241--276 1999 David E. Moriarty Alan C. Schultz John J. Grefenstette: Evolutionary Algorithms for Reinforcement Learning. J. Artif. Intell. Res. (JAIR) 11: 241--276 1999","DOI":"10.1613\/jair.613"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1569901.1570064"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1143997.1144252"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04277-5_77"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/0305-0548(82)90008-9"},{"key":"e_1_3_2_1_13_1","first-page":"158","article-title":"de Jong","author":"Wiering Marco","year":"2007","journal-title":"IEEE ADPRL"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2503308.2503346"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Diederik M. Roijers Peter Vamplew Shimon Whiteson Richard Dazeley: A Survey of Multi-Objective Sequential Decision-Making. J. Artif. Intell. Res. (JAIR) 48: 67--113 (2013) Diederik M. Roijers Peter Vamplew Shimon Whiteson Richard Dazeley: A Survey of Multi-Objective Sequential Decision-Making. J. Artif. Intell. Res. (JAIR) 48: 67--113 (2013)","DOI":"10.1613\/jair.3987"},{"key":"e_1_3_2_1_16_1","first-page":"1","article-title":"Model-based multi-objective reinforcement learning","volume":"2014","author":"Wiering Marco A.","journal-title":"ADPRL"},{"volume-title":"IJCNN","year":"2014","author":"Parisi Simone","key":"e_1_3_2_1_17_1"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"volume-title":"Learning Sets of Pareto Optimal Policies. AAMAS -Adaptive Learning Agents Workshop (ALA)","year":"2014","author":"Moffaert Van","key":"e_1_3_2_1_19_1"},{"volume-title":"IJCNN 2014: 2315--2322","author":"Brys Tim","key":"e_1_3_2_1_20_1"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Weijia Wang Mich\u00e8le Sebag: Hypervolume indicator and dominance reward based multi-objective Monte-Carlo Tree Search. Machine Learning 92(2--3): 403--429 (2013) Weijia Wang Mich\u00e8le Sebag: Hypervolume indicator and dominance reward based multi-objective Monte-Carlo Tree Search. Machine Learning 92(2--3): 403--429 (2013)","DOI":"10.1007\/s10994-013-5369-0"},{"volume-title":"Ann Now\u00e9: Hypervolume-Based Multi-Objective Reinforcement Learning. EMO 2013: 352--366","author":"Moffaert Kristof Van","key":"e_1_3_2_1_22_1"},{"key":"e_1_3_2_1_23_1","first-page":"191","article-title":"Scalarized multi-objective reinforcement learning: Novel design techniques","volume":"2013","author":"Moffaert Kristof Van","journal-title":"ADPRL"},{"first-page":"205","volume-title":"ICML'98","author":"Gabor Z.","key":"e_1_3_2_1_24_1"},{"volume-title":"IJCNN 2013: 1--8","author":"Drugan Madalina M.","key":"e_1_3_2_1_25_1"},{"volume-title":"Marc Schoenauer","year":"2009","author":"Fialho \u00c1lvaro","key":"e_1_3_2_1_26_1"},{"volume-title":"IEEE Congress on Evolutionary Computation 2013: 2078--2085","author":"Puglierin Francesco","key":"e_1_3_2_1_27_1"},{"volume-title":"R\u00e9mi Munos: Best Arm Identification in Multi-Armed Bandits. COLT 2010: 41--53","author":"Audibert Jean-Yves","key":"e_1_3_2_1_28_1"},{"volume-title":"IJCNN 2014: 2690--2697","author":"Drugan Madalina M.","key":"e_1_3_2_1_29_1"},{"volume-title":"Drugan:Linear Scalarization for Pareto Front Identification in Stochastic Environments. EMO 2015: 156--171","author":"Madalina","key":"e_1_3_2_1_30_1"},{"volume-title":"ESANN 2015","author":"Drugan Madalina M.","key":"e_1_3_2_1_31_1"},{"key":"e_1_3_2_1_32_1","first-page":"1","article-title":"Annealing Pareto multi-objective multi-armed bandit algorithm","volume":"2014","author":"Yahyaa Saba Q.","journal-title":"ADPRL"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1068009.1068251"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10472-010-9213-y"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001840"},{"volume-title":"Mich\u00e8le Sebag: Not All Parents Are Equal for MO-CMA-ES. EMO 2011: 31--45","author":"Loshchilov Ilya","key":"e_1_3_2_1_36_1"},{"volume-title":"Talbi El-Ghazali: Adaptive Multi-operator MetaHeuristics for quadratic assignment problems. EVOLVE","year":"2014","author":"Drugan Madalina M","key":"e_1_3_2_1_37_1"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/2576768.2598360"},{"volume-title":"Bernard Manderick: Schemata Bandits for Binary Encoded Combinatorial Optimisation Problems. SEAL 2014: 299--310","author":"Drugan Madalina M.","key":"e_1_3_2_1_39_1"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"volume-title":"IEEE Congress on Evolutionary Computation 2014: 2245--2252","author":"Preux Philippe","key":"e_1_3_2_1_41_1"},{"volume-title":"EVOLVE","year":"2015","author":"Madalina","key":"e_1_3_2_1_42_1"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.4018\/jamc.2010102603"},{"volume-title":"Shimon Whiteson: Queued Pareto Local Search for Multi-Objective Optimization. PPSN 2014: 589--599","author":"Inja Maarten","key":"e_1_3_2_1_44_1"}],"event":{"name":"GECCO '15: Genetic and Evolutionary Computation Conference","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"],"location":"Madrid Spain","acronym":"GECCO '15"},"container-title":["Proceedings of the Companion Publication of the 2015 Annual Conference on Genetic and Evolutionary Computation"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2739482.2756582","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2739482.2756582","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:07:20Z","timestamp":1750223240000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2739482.2756582"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,7,11]]},"references-count":44,"alternative-id":["10.1145\/2739482.2756582","10.1145\/2739482"],"URL":"https:\/\/doi.org\/10.1145\/2739482.2756582","relation":{},"subject":[],"published":{"date-parts":[[2015,7,11]]},"assertion":[{"value":"2015-07-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}