{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:57:25Z","timestamp":1784217445210,"version":"3.55.0"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0119903"],"award-info":[{"award-number":["2022ZD0119903"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2141234"],"award-info":[{"award-number":["U2141234"]}],"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":["62303308"],"award-info":[{"award-number":["62303308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Science and Technology Program","award":["22015810300"],"award-info":[{"award-number":["22015810300"]}]},{"name":"Hainan Province Science and Technology Special Fund","award":["ZDYF2024GXJS003"],"award-info":[{"award-number":["ZDYF2024GXJS003"]}]},{"name":"Joint Research Fund of Shanghai Academy of Spaceflight Technology","award":["USCAST2023-22"],"award-info":[{"award-number":["USCAST2023-22"]}]},{"name":"Shanghai Pujiang Program","award":["23PJ1404700"],"award-info":[{"award-number":["23PJ1404700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tnnls.2024.3481887","type":"journal-article","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:32:54Z","timestamp":1730208774000},"page":"13446-13459","source":"Crossref","is-referenced-by-count":6,"title":["Historical Decision-Making Regularized Maximum Entropy Reinforcement Learning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2026-6856","authenticated-orcid":false,"given":"Botao","family":"Dong","sequence":"first","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-5043","authenticated-orcid":false,"given":"Longyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4322-4314","authenticated-orcid":false,"given":"Ning","family":"Pang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8600-9668","authenticated-orcid":false,"given":"Hongtian","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4700-1276","authenticated-orcid":false,"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning","author":"Sutton","year":"1998"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2024.124227"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3202192"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3156287"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3329513"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3189009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3201511"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2021.1004258"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3276218"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3292253"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3248121"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3049539"},{"key":"ref13","first-page":"1","article-title":"Finite-time analysis of single-timescale actor-critic","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Chen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3213566"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2023.3240585"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.003"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3236361"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3186528"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3296769"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3051456"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121432"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3423417"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390288"},{"key":"ref24","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":"ref25","article-title":"Maximum entropy diverse exploration: Disentangling maximum entropy reinforcement learning","author":"Cohen","year":"2019","journal-title":"arXiv:1911.00828"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3155483"},{"key":"ref27","first-page":"31811","article-title":"Accelerating reinforcement learning with value-conditional state entropy exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Kim"},{"key":"ref28","first-page":"4666","article-title":"Guarantees for \u03f5-greedy reinforcement learning with function approximation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Dann"},{"key":"ref29","first-page":"5093","article-title":"Understanding deep neural function approximation in reinforcement learning via \u03f5-greedy exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Liu"},{"key":"ref30","first-page":"13064","article-title":"On the convergence and sample complexity analysis of deep q-networks with \u03f5-greedy exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhang"},{"key":"ref31","first-page":"78181","article-title":"Monte Carlo tree search with Boltzmann exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Painter"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"ref33","first-page":"317","article-title":"Foresight distribution adjustment for off-policy reinforcement learning","volume-title":"Proc. Int. Conf. Auton. Agents Multiagent Syst.","author":"Chen"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25817"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26281"},{"key":"ref36","first-page":"5940","article-title":"A regularized approach to sparse optimal policy in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/475"},{"key":"ref38","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Schulman"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref40","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref41","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref42","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref43","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref44","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Pan"},{"key":"ref45","first-page":"9443","article-title":"State entropy maximization with random encoders for efficient exploration","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Seo"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3313312"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3009214"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00573-6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3142822"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322426"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3271642"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3280161"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11073756\/10737895.pdf?arnumber=10737895","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T17:49:13Z","timestamp":1752169753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10737895\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":52,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3481887","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}