{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,17]],"date-time":"2026-02-17T14:22:53Z","timestamp":1771338173971,"version":"3.50.1"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3621002","type":"journal-article","created":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:41:52Z","timestamp":1760377312000},"page":"181675-181685","source":"Crossref","is-referenced-by-count":1,"title":["AdvB-TD3: A Novel Decision-Making Framework for Complex Continuous Control Tasks"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7675-7999","authenticated-orcid":false,"given":"Onur","family":"Osman","sequence":"first","affiliation":[{"name":"Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5562-6367","authenticated-orcid":false,"given":"Tolga Kudret","family":"Karaca","sequence":"additional","affiliation":[{"name":"Industrial Engineering Department, Istanbul Topkapi University, Istanbul, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5295-1631","authenticated-orcid":false,"given":"Bahar Yalcin","family":"Kavus","sequence":"additional","affiliation":[{"name":"Quality Coordination Office, İzmir Katip Çelebi University, İzmir, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1906-0401","authenticated-orcid":false,"given":"G\u00f6kalp","family":"Tulum","sequence":"additional","affiliation":[{"name":"Electrical and Electronics Engineering Department, Istanbul Topkapi University, Istanbul, Türkiye"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2020.3044196"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2022.3221805"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/access.2021.3074535"},{"key":"ref5","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref6","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018","journal-title":"arXiv:1802.09477"},{"key":"ref7","first-page":"1","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hasselt"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/bf00115009"},{"key":"ref10","article-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3226446"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2021.120118"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2023.108393"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/s24154962"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3289315"},{"key":"ref16","article-title":"Q-prop: Sample-efficient policy gradient with an off-policy critic","author":"Gu","year":"2016","journal-title":"arXiv:1611.02247"},{"key":"ref17","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref18","article-title":"Trust-PCL: An off-policy trust region method for continuous control","volume-title":"Int. Conf. Learn. Represent","author":"Nachum"},{"key":"ref19","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018","journal-title":"arXiv:1801.01290"},{"key":"ref20","volume-title":"PyBullet, A Python Module for Physics Simulation for Games, Robotics and Machine Learning","author":"Coumans","year":"2016"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11202510.pdf?arnumber=11202510","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T17:40:02Z","timestamp":1761759602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11202510\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3621002","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}