{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T16:19:40Z","timestamp":1781713180247,"version":"3.54.5"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["62373364"],"award-info":[{"award-number":["62373364"]}],"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":["62176259"],"award-info":[{"award-number":["62176259"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2022095"],"award-info":[{"award-number":["BE2022095"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Ind. Inf."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tii.2024.3413308","type":"journal-article","created":{"date-parts":[[2024,6,27]],"date-time":"2024-06-27T21:08:26Z","timestamp":1719522506000},"page":"11785-11793","source":"Crossref","is-referenced-by-count":7,"title":["Offline Reinforcement Learning With Reverse Diffusion Guide Policy"],"prefix":"10.1109","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8963-6374","authenticated-orcid":false,"given":"Jiazhi","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3998-461X","authenticated-orcid":false,"given":"Shuo","family":"Cao","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3240585"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref3","article-title":"Benchmarking batch deep reinforcement learning algorithms","author":"Fujimoto","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3159570"},{"key":"ref5","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3138098"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3292253"},{"key":"ref8","first-page":"40 45240 474","article-title":"Actor-critic alignment for offline-to-online reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2022.3213026"},{"key":"ref10","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3155483"},{"key":"ref12","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref13","first-page":"11 78411 794","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref14","first-page":"28 70128 717","article-title":"Policy regularization with dataset constraint for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ran","year":"2023"},{"key":"ref15","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref16","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov","year":"2021"},{"key":"ref17","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021"},{"key":"ref18","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang","year":"2020"},{"key":"ref19","first-page":"20 13220 145","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fujimoto","year":"2021"},{"key":"ref20","first-page":"23 82923 851","article-title":"Supported trust region optimization for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mao","year":"2023"},{"key":"ref21","first-page":"3682","article-title":"EMaQ: Expected-max Q-learning operator for simple yet effective offline and online RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ghasemipour","year":"2021"},{"key":"ref22","first-page":"20 48520 528","article-title":"Offline reinforcement learning with closed-form policy improvement operators","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref23","article-title":"Dual generator offline reinforcement learning","author":"Vuong","year":"2022"},{"key":"ref24","article-title":"Offline reinforcement learning via high-fidelity generative behavior modeling","author":"Chen","year":"2022"},{"key":"ref25","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal","year":"2021"},{"key":"ref26","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020"},{"key":"ref27","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","author":"Wang","year":"2022"},{"key":"ref28","first-page":"67195","article-title":"Efficient diffusion policies for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kang","year":"2023"},{"key":"ref29","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref31","article-title":"Understanding diffusion models: A unified perspective","author":"Luo","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref33","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2018"},{"key":"ref34","article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","author":"Xiao","year":"2021"},{"key":"ref35","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref36","first-page":"5775","article-title":"DPM-solver: A fast ODE solver for diffusion probabilistic model sampling in around 10 steps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu","year":"2022"}],"container-title":["IEEE Transactions on Industrial Informatics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9424\/10706993\/10574882.pdf?arnumber=10574882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,8]],"date-time":"2024-10-08T17:53:24Z","timestamp":1728410004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10574882\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":36,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tii.2024.3413308","relation":{},"ISSN":["1551-3203","1941-0050"],"issn-type":[{"value":"1551-3203","type":"print"},{"value":"1941-0050","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}