{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:55:14Z","timestamp":1768294514417,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T00:00:00Z","timestamp":1689120000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Vingroup Innovation Foundation (VINIF)","award":["VINIF.2022.DA00183"],"award-info":[{"award-number":["VINIF.2022.DA00183"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,15]]},"DOI":"10.1145\/3583131.3590441","type":"proceedings-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T19:40:19Z","timestamp":1689190819000},"page":"577-585","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["A Two-Stage Multi-Objective Evolutionary Reinforcement Learning Framework for Continuous Robot Control"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3577-7623","authenticated-orcid":false,"given":"Hai-Long","family":"Tran","sequence":"first","affiliation":[{"name":"Hanoi University of Science and Technology, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6338-7916","authenticated-orcid":false,"given":"Long","family":"Doan","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, Virginia, United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6768-1950","authenticated-orcid":false,"given":"Ngoc Hoang","family":"Luong","sequence":"additional","affiliation":[{"name":"University of Information Technology (UIT), VNU-HCM, Ho Chi Minh City, Vietnam"},{"name":"Vietnam National University - Ho Chi Minh City (VNU-HCM), Ho Chi Minh City, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1976-6113","authenticated-orcid":false,"given":"Huynh Thi Thanh","family":"Binh","sequence":"additional","affiliation":[{"name":"Hanoi University of Science and Technology, Hanoi, Vietnam"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"S\u00e9bastien Le Digabel, and Ludovic Salomon","author":"Audet Charles","year":"2021","unstructured":"Charles Audet , Jean Bigeon , Dominique Cartier , S\u00e9bastien Le Digabel, and Ludovic Salomon . 2021 . Performance indicators in multiobjective optimization. European journal of operational research 292, 2 (2021), 397--422. Charles Audet, Jean Bigeon, Dominique Cartier, S\u00e9bastien Le Digabel, and Ludovic Salomon. 2021. Performance indicators in multiobjective optimization. European journal of operational research 292, 2 (2021), 397--422."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5728"},{"key":"e_1_3_2_1_3_1","volume-title":"Openai gym. arXiv preprint arXiv:1606.01540","author":"Brockman Greg","year":"2016","unstructured":"Greg Brockman , Vicki Cheung , Ludwig Pettersson , Jonas Schneider , John Schulman , Jie Tang , and Wojciech Zaremba . 2016. Openai gym. arXiv preprint arXiv:1606.01540 ( 2016 ). Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. Openai gym. arXiv preprint arXiv:1606.01540 (2016)."},{"key":"e_1_3_2_1_4_1","volume-title":"ECAI","author":"Chen Diqi","year":"2020","unstructured":"Diqi Chen , Yizhou Wang , and Wen Gao . 2020 . A two-stage multi-objective deep reinforcement learning framework . In ECAI 2020. IOS Press, 1063--1070. Diqi Chen, Yizhou Wang, and Wen Gao. 2020. A two-stage multi-objective deep reinforcement learning framework. In ECAI 2020. IOS Press, 1063--1070."},{"key":"e_1_3_2_1_5_1","volume-title":"A fast and elitist multiobjective genetic algorithm: NSGA-II","author":"Deb Kalyanmoy","year":"2002","unstructured":"Kalyanmoy Deb , Amrit Pratap , Sameer Agarwal , and TAMT Meyarivan . 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II . IEEE transactions on evolutionary computation 6, 2 ( 2002 ), 182--197. Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and TAMT Meyarivan. 2002. A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE transactions on evolutionary computation 6, 2 (2002), 182--197."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1061\/(ASCE)WR.1943-5452.0000570"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.4018\/jats.2009040104"},{"key":"e_1_3_2_1_8_1","volume-title":"Evolution-guided policy gradient in reinforcement learning. Advances in Neural Information Processing Systems 31","author":"Khadka Shauharda","year":"2018","unstructured":"Shauharda Khadka and Kagan Tumer . 2018. Evolution-guided policy gradient in reinforcement learning. Advances in Neural Information Processing Systems 31 ( 2018 ). Shauharda Khadka and Kagan Tumer. 2018. Evolution-guided policy gradient in reinforcement learning. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205473"},{"key":"e_1_3_2_1_10_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap Timothy P","year":"2015","unstructured":"Timothy P Lillicrap , Jonathan J Hunt , Alexander Pritzel , Nicolas Heess , Tom Erez , Yuval Tassa , David Silver , and Daan Wierstra . 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 ( 2015 ). Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.11.094"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889738"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512290.3528823"},{"key":"e_1_3_2_1_14_1","first-page":"15","article-title":"A temporal difference method for multi-objective reinforcement learning","volume":"263","author":"Ruiz-Montiel Manuela","year":"2017","unstructured":"Manuela Ruiz-Montiel , Lawrence Mandow , and Jos\u00e9-Luis P\u00e9rez-de- la Cruz . 2017 . A temporal difference method for multi-objective reinforcement learning . Neuro-computing 263 (2017), 15 -- 25 . Manuela Ruiz-Montiel, Lawrence Mandow, and Jos\u00e9-Luis P\u00e9rez-de-la Cruz. 2017. A temporal difference method for multi-objective reinforcement learning. Neuro-computing 263 (2017), 15--25.","journal-title":"Neuro-computing"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63773-6"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001674"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"e_1_3_2_1_19_1","first-page":"3483","article-title":"Multi-objective reinforcement learning using sets of pareto dominating policies","volume":"15","author":"Moffaert Kristof Van","year":"2014","unstructured":"Kristof Van Moffaert and Ann Now\u00e9 . 2014 . Multi-objective reinforcement learning using sets of pareto dominating policies . The Journal of Machine Learning Research 15 , 1 (2014), 3483 -- 3512 . Kristof Van Moffaert and Ann Now\u00e9. 2014. Multi-objective reinforcement learning using sets of pareto dominating policies. The Journal of Machine Learning Research 15, 1 (2014), 3483--3512.","journal-title":"The Journal of Machine Learning Research"},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning. PMLR, 10607--10616","author":"Xu Jie","year":"2020","unstructured":"Jie Xu , Yunsheng Tian , Pingchuan Ma , Daniela Rus , Shinjiro Sueda , and Wojciech Matusik . 2020 . Prediction-guided multi-objective reinforcement learning for continuous robot control . In International conference on machine learning. PMLR, 10607--10616 . Jie Xu, Yunsheng Tian, Pingchuan Ma, Daniela Rus, Shinjiro Sueda, and Wojciech Matusik. 2020. Prediction-guided multi-objective reinforcement learning for continuous robot control. In International conference on machine learning. PMLR, 10607--10616."},{"key":"e_1_3_2_1_21_1","volume-title":"Algorithms for partially observable Markov decision processes","author":"Zhang Weihong","unstructured":"Weihong Zhang . 2001. Algorithms for partially observable Markov decision processes . Hong Kong University of Science and Technology (Hong Kong) . Weihong Zhang. 2001. Algorithms for partially observable Markov decision processes. Hong Kong University of Science and Technology (Hong Kong)."}],"event":{"name":"GECCO '23: Genetic and Evolutionary Computation Conference","location":"Lisbon Portugal","acronym":"GECCO '23","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"]},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583131.3590441","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3583131.3590441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:03Z","timestamp":1750178823000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3583131.3590441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,12]]},"references-count":20,"alternative-id":["10.1145\/3583131.3590441","10.1145\/3583131"],"URL":"https:\/\/doi.org\/10.1145\/3583131.3590441","relation":{},"subject":[],"published":{"date-parts":[[2023,7,12]]},"assertion":[{"value":"2023-07-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}