{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T23:36:56Z","timestamp":1793921816703,"version":"4.8.0"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92267110"],"award-info":[{"award-number":["92267110"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076202"],"award-info":[{"award-number":["62076202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61976178"],"award-info":[{"award-number":["61976178"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Projects of Zhejiang Lab","award":["2022NB0AB07"],"award-info":[{"award-number":["2022NB0AB07"]}]},{"name":"Shaanxi Province Key Research and Development Program of China","award":["2023-YBGY-354"],"award-info":[{"award-number":["2023-YBGY-354"]}]},{"name":"Shaanxi Province Key Research and Development Program of China","award":["2022GY-249"],"award-info":[{"award-number":["2022GY-249"]}]},{"name":"Shaanxi Province Key Research and Development Program of China","award":["2022GY-090"],"award-info":[{"award-number":["2022GY-090"]}]},{"name":"CAAI-Huawei MindSpore Open Fund","award":["CAAIXSJLJJ-2021-041A"],"award-info":[{"award-number":["CAAIXSJLJJ-2021-041A"]}]},{"name":"Innovation Foundation of Northwestern Polytechnical University","award":["CX2022016"],"award-info":[{"award-number":["CX2022016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Emerg. Top. Comput. Intell."],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1109\/tetci.2023.3326551","type":"journal-article","created":{"date-parts":[[2023,10,31]],"date-time":"2023-10-31T14:48:50Z","timestamp":1698763730000},"page":"1030-1043","source":"Crossref","is-referenced-by-count":19,"title":["DeRL: Coupling Decomposition in Action Space for Reinforcement Learning Task"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-2218-8550","authenticated-orcid":false,"given":"Ziming","family":"He","sequence":"first","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0905-0816","authenticated-orcid":false,"given":"Jingchen","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7143-1661","authenticated-orcid":false,"given":"Fan","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2180-8941","authenticated-orcid":false,"given":"Haobin","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Computer Science, Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9234-4836","authenticated-orcid":false,"given":"Kao-Shing","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"1","key":"ref1","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref2","first-page":"21847","article-title":"Accelerating robotic reinforcement learning via parameterized action primitives","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Dalal","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/832"},{"key":"ref4","first-page":"10784","article-title":"Learning to simulate self-driven particles system with coordinated policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Peng","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3083410"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3098354"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref8","first-page":"689","article-title":"Safe and nested subgame solving for imperfect-information games","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2017"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref10","first-page":"1052","article-title":"Generative adversarial user model for reinforcement learning based recommendation system","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2021.0068"},{"key":"ref12","article-title":"An overview of multi-agent reinforcement learning from game theoretical perspective","author":"Yang","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref14","first-page":"1889","article-title":"Trust region policy optimiz ation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref15","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref16","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver","year":"2014"},{"key":"ref17","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap","year":"2016"},{"key":"ref18","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","year":"2018"},{"key":"ref19","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967959"},{"key":"ref21","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-019-0470-8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.2978-14.2015"},{"key":"ref24","first-page":"4742","article-title":"Structured control nets for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Srouji","year":"2018"},{"key":"ref25","first-page":"9870","article-title":"Decoupling representation learning from reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Stooke","year":"2021"},{"key":"ref26","article-title":"Is independent learning all you need in the starcraft multi-agent challenge?","author":"De Witt","year":"2020"},{"key":"ref27","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref29","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. AAAI Fall Symp. Ser.","author":"Hausknecht","year":"2015"},{"key":"ref30","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Iqbal","year":"2019"},{"key":"ref31","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lowe","year":"2017"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2022.3170646"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3108237"},{"key":"ref34","article-title":"Actor-critic algorithms","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda","year":"1999"},{"key":"ref35","first-page":"679","article-title":"A Markov decision process","volume":"6","author":"Bellman","year":"1957","journal-title":"J. Math. Mechanics"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.106685"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3985"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1002\/wics.101"},{"key":"ref39","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref42","article-title":"Opening the black box of deep neural networks via information","author":"Shwartz-Ziv","year":"2017"},{"key":"ref43","volume-title":"Elements of Information Theory","author":"Thomas","year":"2006"},{"key":"ref44","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach, Learn.","author":"Haarnoja","year":"2017"},{"key":"ref45","article-title":"Spinning up in deep reinforcement learning","volume-title":"Proc. GitHub Repository","author":"Achiam","year":"2018"},{"key":"ref46","article-title":"DERL: Decoupled reinforcement learning","volume-title":"Proc. GitHub Repository","author":"He","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref48","article-title":"Openai gym","author":"Brockman","year":"2016"},{"key":"ref49","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005601"}],"container-title":["IEEE Transactions on Emerging Topics in Computational Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7433297\/10412693\/10302327.pdf?arnumber=10302327","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T14:00:09Z","timestamp":1732629609000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10302327\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":50,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tetci.2023.3326551","relation":{},"ISSN":["2471-285X"],"issn-type":[{"value":"2471-285X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]}}}