{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T18:24:10Z","timestamp":1783794250884,"version":"3.55.0"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61901183"],"award-info":[{"award-number":["61901183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFE0205400"],"award-info":[{"award-number":["2021YFE0205400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Innovation Platform Project of Fujian Province","award":["2021FX03"],"award-info":[{"award-number":["2021FX03"]}]},{"DOI":"10.13039\/501100005270","name":"Natural Science Foundation of Fujian Provincial Science and Technology Department","doi-asserted-by":"publisher","award":["2021H6037"],"award-info":[{"award-number":["2021H6037"]}],"id":[{"id":"10.13039\/501100005270","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2019J01010561"],"award-info":[{"award-number":["2019J01010561"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["ZQN-921"],"award-info":[{"award-number":["ZQN-921"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Foundation of Fujian Education Department","award":["JAT170053"],"award-info":[{"award-number":["JAT170053"]}]},{"name":"Key Project of Quanzhou Science and Technology Plan","award":["2021C008R"],"award-info":[{"award-number":["2021C008R"]}]},{"DOI":"10.13039\/501100018624","name":"Science and Technology Bureau of Quanzhou","doi-asserted-by":"publisher","award":["2017G046"],"award-info":[{"award-number":["2017G046"]}],"id":[{"id":"10.13039\/501100018624","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3226446","type":"journal-article","created":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T20:57:09Z","timestamp":1670014629000},"page":"128077-128089","source":"Crossref","is-referenced-by-count":33,"title":["A-TD3: An Adaptive Asynchronous Twin Delayed Deep Deterministic for Continuous Action Spaces"],"prefix":"10.1109","volume":"10","author":[{"given":"Jiaolv","family":"Wu","sequence":"first","affiliation":[{"name":"College of Engineering Institute, Huaqiao University, Quanzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5208-7975","authenticated-orcid":false,"given":"Q. M. Jonathan","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuyue","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Mathematics and Statistic, Shenzhen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7122-9975","authenticated-orcid":false,"given":"Farhad","family":"Pourpanah","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Windsor, Windsor, ON, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8542-3728","authenticated-orcid":false,"given":"Detian","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Engineering Institute, Huaqiao University, Quanzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref38","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref33","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref32","first-page":"1","article-title":"Massively parallel methods for deep reinforcement learning","author":"nair","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3154718"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107128"},{"key":"ref37","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref35","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc ICML"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1080\/00224065.1986.11979014","article-title":"The exponentially weighted moving average","volume":"18","author":"stuart","year":"1986","journal-title":"J Quality Technol"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.08.023"},{"key":"ref11","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref12","first-page":"1064","article-title":"Monte Carlo pomdps","volume":"12","author":"thrun","year":"1999","journal-title":"Proc NIPS"},{"key":"ref13","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref14","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","first-page":"1","article-title":"Parallel reinforcement learning","author":"kretchmar","year":"2002","journal-title":"Proc 6th World Conf Systemics Cybern Inform"},{"key":"ref16","first-page":"60","article-title":"Parallel reinforcement learning with linear function approximation","author":"grounds","year":"2005","journal-title":"Adaptive Agents and Multi-Agent Systems III Adaptation and Multi-Agent Learning"},{"key":"ref17","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"10124","article-title":"An efficient asynchronous method for integrating evolutionary and gradient-based policy search","volume":"33","author":"lee","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"salimans","year":"2017","journal-title":"arXiv 1703 03864"},{"key":"ref28","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.067"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3169907"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107660"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-04357-7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.002"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-018-0843-4"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2021.3117565"},{"key":"ref9","first-page":"222","article-title":"Accelerated reward policy (ARP) for robotics deep reinforcement learning","volume":"2","author":"patil","year":"2022","journal-title":"Proc Future Inf Commun Conf"},{"key":"ref1","first-page":"126","article-title":"Reinforcement learning","volume":"11","author":"sutton","year":"1999","journal-title":"J Cognit Neurosci"},{"key":"ref20","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":"ref22","volume":"37","author":"rummery","year":"1994","journal-title":"On-line Q-learning using connectionist systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-018-1241-z"},{"key":"ref24","first-page":"1","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref26","first-page":"1","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"Proc NIPS"},{"key":"ref25","first-page":"233","article-title":"Learning from delayed rewards","volume":"15","author":"watkins","year":"1989","journal-title":"Robotics and Autonomous System"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09969602.pdf?arnumber=9969602","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,9]],"date-time":"2023-01-09T21:27:39Z","timestamp":1673299659000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9969602\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3226446","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}