{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T01:05:07Z","timestamp":1759971907800,"version":"build-2065373602"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFE0106300"],"award-info":[{"award-number":["2023YFE0106300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62250710682","62476119"],"award-info":[{"award-number":["62250710682","62476119"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Major Project of Basic and Applied Basic Research","award":["2023B0303000010"],"award-info":[{"award-number":["2023B0303000010"]}]},{"DOI":"10.13039\/501100015973","name":"Internal Grants of Lingnan University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100015973","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tnnls.2025.3582299","type":"journal-article","created":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T13:38:56Z","timestamp":1751981936000},"page":"19327-19341","source":"Crossref","is-referenced-by-count":0,"title":["Robust Dynamic Material Handling via Adaptive Constrained Evolutionary Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-4186","authenticated-orcid":false,"given":"Chengpeng","family":"Hu","sequence":"first","affiliation":[{"name":"Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, Eindhoven, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziming","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9899-8961","authenticated-orcid":false,"given":"Bo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7047-8454","authenticated-orcid":false,"given":"Jialin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Data Science, Lingnan University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5715-7154","authenticated-orcid":false,"given":"Chengqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Data Science and Artificial Intelligence, The Hong Kong Polytechnic University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8837-4442","authenticated-orcid":false,"given":"Xin","family":"Yao","sequence":"additional","affiliation":[{"name":"School of Data Science, Lingnan University, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.106881"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2021.08.008"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10951-008-0090-8"},{"issue":"2","key":"ref4","first-page":"32","article-title":"A multi-agent based approach to dynamic scheduling of machines and automated guided vehicles (AGV) in manufacturing systems by considering AGV breakdowns","volume":"7","author":"Kaplano\u011flu","year":"2015","journal-title":"Int. J. Eng. Res. Innov."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191999"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2020.106749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2021.11.305"},{"key":"ref8","first-page":"13049","article-title":"Emergent complexity and zero-shot transfer via unsupervised environment design","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Dennis"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1080\/00207548208947745"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/002075498193877"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011253011638"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2018.8632448"},{"key":"ref13","first-page":"1","article-title":"Reinforcement learning and the reward engineering principle","volume-title":"Proc. AAAI Spring Symp. Ser.","author":"Dewey"},{"key":"ref14","first-page":"278","article-title":"Policy invariance under reward transformations: Theory and application to reward shaping","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"99","author":"Ng"},{"key":"ref15","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Achiam"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref17","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017","journal-title":"arXiv:1703.03864"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107731"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cie.2007.08.008"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/00207543.2010.510486"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WF-IoT.2018.8355151"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cor.2018.05.009"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00170-015-7329-2"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.rcim.2019.101849"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3211507"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3164242"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref29","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10845-013-0852-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICIT.2018.8352413"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.procir.2020.05.210"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3520381"},{"key":"ref34","first-page":"1479","article-title":"Unifying count-based exploration and intrinsic motivation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Bellemare"},{"key":"ref35","first-page":"1117","article-title":"VIME: Variational information maximizing exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Houthooft"},{"key":"ref36","first-page":"1","article-title":"Reward constrained policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Tessler"},{"key":"ref37","first-page":"4940","article-title":"Prioritized level replay","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jiang"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/5.784219"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3569096"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.34133\/icomputing.0025"},{"key":"ref41","article-title":"Deep neuroevolution: Genetic algorithms are a competitive alternative for training deep neural networks for reinforcement learning","author":"Such","year":"2017","journal-title":"arXiv:1712.06567"},{"key":"ref42","first-page":"5027","article-title":"Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Conti"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2021.100974"},{"key":"ref44","first-page":"1196","article-title":"Evolution-guided policy gradient in reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Khadka"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191982"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.2307\/1427934"},{"key":"ref47","first-page":"1","article-title":"Bootstrapping upper confidence bound","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Hao"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-39883-7_3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/4235.873238"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/0-306-48041-7_4"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2009.2023449"},{"issue":"1","key":"ref52","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"Wierstra","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref54","first-page":"10299","article-title":"From complexity to simplicity: Adaptive ES-active subspaces for blackbox optimization","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Choroma\u00b4nski"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/205"},{"key":"ref56","first-page":"387","article-title":"Policy gradients with variance related risk criteria","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tamar"},{"key":"ref57","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"issue":"267","key":"ref58","first-page":"1","article-title":"Tianshou: A highly modularized deep reinforcement learning library","volume":"23","author":"Weng","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref59","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11195929\/11073151.pdf?arnumber=11073151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T17:38:56Z","timestamp":1759945136000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11073151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":59,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3582299","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}