{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:27:07Z","timestamp":1775143627038,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T00:00:00Z","timestamp":1720915200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276100"],"award-info":[{"award-number":["62276100"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Natural Science Funds for Distinguished Young Scholars","award":["2022B1515020049"],"award-info":[{"award-number":["2022B1515020049"]}]},{"name":"Guangdong Regional Joint Funds for Basic and Applied Research","award":["2021B1515120078"],"award-info":[{"award-number":["2021B1515120078"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,14]]},"DOI":"10.1145\/3638529.3653996","type":"proceedings-article","created":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T16:33:04Z","timestamp":1720456384000},"page":"1497-1505","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Auto-configuring Exploration-Exploitation Tradeoff in Evolutionary Computation via Deep Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6216-9379","authenticated-orcid":false,"given":"Zeyuan","family":"Ma","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7539-6156","authenticated-orcid":false,"given":"Jiacheng","family":"Chen","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8063-8984","authenticated-orcid":false,"given":"Hongshu","family":"Guo","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6639-8547","authenticated-orcid":false,"given":"Yining","family":"Ma","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5648-1160","authenticated-orcid":false,"given":"Yue-Jiao","family":"Gong","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2024,7,14]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0161558"},{"key":"e_1_3_2_2_2_1","volume-title":"Proceedings of the 30th Conference on Neural Information Processing Systems.","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. In Proceedings of the 30th Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_2_3_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Chen Jiacheng","year":"2024","unstructured":"Jiacheng Chen, Zeyuan Ma, Hongshu Guo, Yining Ma, Jie Zhang, and Yue-jiao Gong. 2024. Symbol: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCA.2009.2012436"},{"key":"e_1_3_2_2_5_1","volume-title":"A hybrid particle swarm optimizer with sine cosine acceleration coefficients. Information Sciences 422, -","author":"Chen Ke","year":"2018","unstructured":"Ke Chen, Fengyu Zhou, Lei Yin, Shuqian Wang, Yugang Wang, and Fang Wan. 2018. A hybrid particle swarm optimizer with sine cosine acceleration coefficients. Information Sciences 422, - (2018), 218--241."},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/4235.985692"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098043"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2475174"},{"key":"e_1_3_2_2_9_1","volume-title":"Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution","author":"Guo Hongshu","year":"2024","unstructured":"Hongshu Guo, Yining Ma, Zeyuan Ma, Jiacheng Chen, Xinglin Zhang, Zhiguang Cao, Jun Zhang, and Yue-Jiao Gong. 2024. Deep Reinforcement Learning for Dynamic Algorithm Selection: A Proof-of-Principle Study on Differential Evolution. IEEE Transactions on Systems, Man, and Cybernetics: Systems. to be published (2024), to be published."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/prot.22830"},{"key":"e_1_3_2_2_11_1","volume-title":"Proceedings of the 32nd International conference on machine learning. 448--456","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In Proceedings of the 32nd International conference on machine learning. 448--456."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1995.488968"},{"key":"e_1_3_2_2_13_1","volume-title":"Pomo: Policy optimization with multiple optima for reinforcement learning. Advances in Neural Information Processing Systems 33, -","author":"Kwon Yeong-Dae","year":"2020","unstructured":"Yeong-Dae Kwon, Jinho Choo, Byoungjip Kim, Iljoo Yoon, Youngjune Gwon, and Seungjai Min. 2020. Pomo: Policy optimization with multiple optima for reinforcement learning. Advances in Neural Information Processing Systems 33, - (2020), 21188--21198."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590496"},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the 11th International Conference on Learning Representations.","author":"Lange Robert Tjarko","year":"2022","unstructured":"Robert Tjarko Lange, Tom Schaul, Yutian Chen, Tom Zahavy, Valentin Dalibard, Chris Lu, Satinder Singh, and Sebastian Flennerhag. 2022. Discovering Evolution Strategies via Meta-Black-Box Optimization. In Proceedings of the 11th International Conference on Learning Representations."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2015.7257290"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/SIS.2005.1501611"},{"key":"e_1_3_2_2_18_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)."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2019.8790035"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2017.02.007"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/662"},{"key":"e_1_3_2_2_22_1","volume-title":"MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning. Advances in Neural Information Processing Systems 36","author":"Ma Zeyuan","year":"2023","unstructured":"Zeyuan Ma, Hongshu Guo, Jiacheng Chen, Zhenrui Li, Guojun Peng, Yue-Jiao Gong, Yining Ma, and Zhiguang Cao. 2023. MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning. Advances in Neural Information Processing Systems 36 (2023)."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/664"},{"key":"e_1_3_2_2_24_1","volume-title":"Proceedings of the 2021 IEEE Congress on Evolutionary Computation.","author":"Mohamed Ali Wagdy","unstructured":"Ali Wagdy Mohamed, Anas A Hadi, Ali Khater Mohamed, Prachi Agrawal, Abhishek Kumar, and P. N. Suganthan. 2021. Problem definitions and evaluation criteria for the cec 2021 on Single Objective Bound Constrained Numerical Optimization. In Proceedings of the 2021 IEEE Congress on Evolutionary Computation."},{"key":"e_1_3_2_2_25_1","volume-title":"Fuzzy Self-Tuning PSO: A settings-free algorithm for global optimization. Swarm and Evolutionary Computation 39, -","author":"Nobile Marco S","year":"2018","unstructured":"Marco S Nobile, Paolo Cazzaniga, Daniela Besozzi, Riccardo Colombo, Giancarlo Mauri, and Gabriella Pasi. 2018. Fuzzy Self-Tuning PSO: A settings-free algorithm for global optimization. Swarm and Evolutionary Computation 39, - (2018), 70--85."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2004.826071"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.01.006"},{"key":"e_1_3_2_2_28_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321813"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICEC.1998.699146"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.1999.785511"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-04832-8"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3060811"},{"key":"e_1_3_2_2_35_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_2_36_1","volume-title":"Differential evolution with mixed mutation strategy based on deep reinforcement learning. Applied Soft Computing 111, -","author":"Tan Zhiping","year":"2021","unstructured":"Zhiping Tan and Kangshun Li. 2021. Differential evolution with mixed mutation strategy based on deep reinforcement learning. Applied Soft Computing 111, - (2021), 107678."},{"key":"e_1_3_2_2_37_1","volume-title":"Differential evolution with hybrid parameters and mutation strategies based on reinforcement learning. Swarm and Evolutionary Computation 75, -","author":"Tan Zhiping","year":"2022","unstructured":"Zhiping Tan, Yu Tang, Kangshun Li, Huasheng Huang, and Shaoming Luo. 2022. Differential evolution with hybrid parameters and mutation strategies based on reinforcement learning. Swarm and Evolutionary Computation 75, - (2022), 101194."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2014.6900380"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.09.053"},{"key":"e_1_3_2_2_40_1","volume-title":"Evolution Transformer: In-Context Evolutionary Optimization. arXiv e-prints","author":"Lange Robert Tjarko","year":"2024","unstructured":"Robert Tjarko Lange, Yingtao Tian, and Yujin Tang. 2024. Evolution Transformer: In-Context Evolutionary Optimization. arXiv e-prints (2024), arXiv-2403."},{"key":"e_1_3_2_2_41_1","volume-title":"Proceedings of the 31th Conference on Neural Information Processing Systems. 5998--6008","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the 31th Conference on Neural Information Processing Systems. 5998--6008."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-016-2474-6"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1080\/0305215X.2020.1867120"},{"key":"e_1_3_2_2_44_1","volume-title":"A fitness-based multi-role particle swarm optimization. Swarm and Evolutionary Computation 44, -","author":"Xia Xuewen","year":"2019","unstructured":"Xuewen Xia, Ying Xing, Bo Wei, Yinglong Zhang, Xiong Li, Xianli Deng, and Ling Gui. 2019. A fitness-based multi-role particle swarm optimization. Swarm and Evolutionary Computation 44, - (2019), 349--364."},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04527-9"},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings of the 4th International Conference on Algorithms, Computing and Artificial Intelligence. 1--6.","author":"Yin Shiyuan","year":"2021","unstructured":"Shiyuan Yin, Yi Liu, GuoLiang Gong, Huaxiang Lu, and Wenchang Li. 2021. RLEPSO: Reinforcement learning based Ensemble particle swarm optimizer*. In Proceedings of the 4th International Conference on Algorithms, Computing and Artificial Intelligence. 1--6."},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of the 33th Conference on Neural Information Processing Systems. 17283--17297","author":"Zaheer Manzil","year":"2020","unstructured":"Manzil Zaheer, Guru Guruganesh, Kumar Avinava Dubey, Joshua Ainslie, Chris Alberti, Santiago Ontanon, Philip Pham, Anirudh Ravula, Qifan Wang, Li Yang, et al. 2020. Big bird: Transformers for longer sequences. In Proceedings of the 33th Conference on Neural Information Processing Systems. 17283--17297."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2009.2014613"}],"event":{"name":"GECCO '24: Genetic and Evolutionary Computation Conference","location":"Melbourne VIC Australia","acronym":"GECCO '24","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\/3638529.3653996","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3638529.3653996","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:56:49Z","timestamp":1750291009000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3638529.3653996"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,14]]},"references-count":48,"alternative-id":["10.1145\/3638529.3653996","10.1145\/3638529"],"URL":"https:\/\/doi.org\/10.1145\/3638529.3653996","relation":{},"subject":[],"published":{"date-parts":[[2024,7,14]]},"assertion":[{"value":"2024-07-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}