{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:20:08Z","timestamp":1774365608775,"version":"3.50.1"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s40747-025-01852-6","type":"journal-article","created":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T06:15:02Z","timestamp":1745561702000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Directly Attention loss adjusted prioritized experience replay"],"prefix":"10.1007","volume":"11","author":[{"given":"Zhuoying","family":"Chen","sequence":"first","affiliation":[]},{"given":"Huiping","family":"Li","sequence":"additional","affiliation":[]},{"given":"Zhaoxu","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"issue":"3","key":"1852_CR1","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/BF00992699","volume":"8","author":"L Lin","year":"1992","unstructured":"Lin L (1992) Self-improving reactive agents based on reinforcement learning, planning and teaching. Mach Learn 8(3):293\u2013321","journal-title":"Mach Learn"},{"issue":"2","key":"1852_CR2","first-page":"5643","volume":"6","author":"A Kumar","year":"2024","unstructured":"Kumar A (2024) SURF feature descriptor for image analysis. Mach Learn 6(2):5643\u20135652","journal-title":"Mach Learn"},{"key":"1852_CR3","doi-asserted-by":"publisher","first-page":"119","DOI":"10.37394\/23208.2023.20.12","volume":"20","author":"AK Aggarwal","year":"2023","unstructured":"Aggarwal AK (2023) A review on genomics data analysis using machine learning. WSEAS Trans Biol Biomed 20:119\u2013131","journal-title":"WSEAS Trans Biol Biomed"},{"key":"1852_CR4","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2016) Prioritized experience replay. In: International conference on learning representations"},{"key":"1852_CR5","doi-asserted-by":"crossref","unstructured":"Bu F, Chang D (2020) Double prioritized state recycled experience replay. In: IEEE international conference on consumer electronics, pp 1\u20136","DOI":"10.1109\/ICCE-Asia49877.2020.9276975"},{"issue":"7540","key":"1852_CR6","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"issue":"12","key":"1852_CR7","doi-asserted-by":"publisher","first-page":"7363","DOI":"10.1109\/TSMC.2020.2967936","volume":"51","author":"J Sharma","year":"2021","unstructured":"Sharma J, Andersen PA, Granmo OC, Goodwin M (2021) Deep Q-learning with Q-matrix transfer learning for novel fire evacuation environment. IEEE Trans Syst Man Cybern Syst 51(12):7363\u20137381","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"12","key":"1852_CR8","doi-asserted-by":"publisher","first-page":"11547","DOI":"10.1109\/JIOT.2020.3022611","volume":"7","author":"X Tao","year":"2020","unstructured":"Tao X, Hafid AS (2020) DeepSensing: a novel mobile crowdsensing framework with double deep q-network and prioritized experience replay. IEEE Internet Things J 7(12):11547\u201311558","journal-title":"IEEE Internet Things J"},{"key":"1852_CR9","unstructured":"Yue Y, Kang B (2023) Offline prioritized experience replay. arXiv:2306.05412"},{"issue":"5","key":"1852_CR10","doi-asserted-by":"publisher","first-page":"3150","DOI":"10.1109\/TII.2021.3106402","volume":"18","author":"R Yang","year":"2022","unstructured":"Yang R, Wang D, Qiao J (2022) Policy gradient adaptive critic design with dynamic prioritized experience replay for wastewater treatment process control. IEEE Trans Ind Inf 18(5):3150\u20133158","journal-title":"IEEE Trans Ind Inf"},{"key":"1852_CR11","unstructured":"Fujimoto S, Meger D, Precup D (2020) An equivalence between loss functions and non-uniform sampling in experience replay. In: Proceedings of the 34th international conference on neural information processing systems, vol 33, pp 14219\u201314230"},{"key":"1852_CR12","doi-asserted-by":"crossref","unstructured":"Saglam B, Mutlu FB, Cicek DC, Kozat SS (2022) Actor prioritized experience replay. arXiv:2209.00532","DOI":"10.1613\/jair.1.14819"},{"key":"1852_CR13","unstructured":"Chen ZY, Li HP, Wang RZ (2023) Attention loss adjusted prioritized experience replay. arXiv:2309.06684"},{"key":"1852_CR14","doi-asserted-by":"crossref","unstructured":"Gao J, Li X, Liu W, Zhao J (2021) Prioritized experience replay method based on experience reward. In: International conference on machine learning and intelligent systems engineering, pp 214\u2013219","DOI":"10.1109\/MLISE54096.2021.00045"},{"key":"1852_CR15","unstructured":"Gruslys A, Dabney W (2017) The reactor: a fast and sample-efficient actor-critic agent for reinforcement learning. arXiv:1704.04651"},{"key":"1852_CR16","doi-asserted-by":"crossref","unstructured":"Sun P, Zhou W, Li H (2020) Attentive experience replay. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, no 4, pp 5900\u20135907","DOI":"10.1609\/aaai.v34i04.6049"},{"key":"1852_CR17","unstructured":"Brittain M, Bertram J, Yang X, Wei P (2020) Prioritized sequence experience replay. arXiv:2002.12726"},{"key":"1852_CR18","doi-asserted-by":"crossref","unstructured":"Xing X, Zhou Z, Li Y (2024) Multi-UAV adaptive cooperative formation trajectory planning based on an improved MATD3 algorithm of deep reinforcement learning. IEEE Trans Veh Technol 73(9):12484\u201312499","DOI":"10.1109\/TVT.2024.3389555"},{"issue":"8","key":"1852_CR19","doi-asserted-by":"publisher","first-page":"4831","DOI":"10.1109\/LRA.2023.3290511","volume":"8","author":"H Zhang","year":"2023","unstructured":"Zhang H, Wang H, Kan Z (2023) Exploiting transformer in sparse reward reinforcement learning for interpretable temporal logic motion planning. IEEE Robot Autom Lett 8(8):4831\u20134838","journal-title":"IEEE Robot Autom Lett"},{"key":"1852_CR20","doi-asserted-by":"crossref","unstructured":"Zhao H, Wu J, Li Z, Chen W, Zheng Z (2023) Double sparse deep reinforcement learning via multilayer sparse coding and nonconvex regularized pruning. IEEE Trans Cybern 53(2):765\u2013778","DOI":"10.1109\/TCYB.2022.3157892"},{"key":"1852_CR21","doi-asserted-by":"publisher","first-page":"109301","DOI":"10.1109\/ACCESS.2019.2933454","volume":"7","author":"G Zhang","year":"2019","unstructured":"Zhang G, Li Y, Xu X, Dai H (2019) Efficient training techniques for multi-agent reinforcement learning in combat tasks. IEEE Access 7:109301\u2013109310","journal-title":"IEEE Access"},{"key":"1852_CR22","doi-asserted-by":"crossref","unstructured":"Chen Z, Li H, Wang R, Cui D (2024) Progressive prioritized experience replay for multi-agent reinforcement learning. In: Chinese control conference","DOI":"10.23919\/CCC63176.2024.10661678"}],"container-title":["Complex & Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01852-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-025-01852-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-025-01852-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,17]],"date-time":"2025-05-17T11:22:43Z","timestamp":1747480963000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-025-01852-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":22,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["1852"],"URL":"https:\/\/doi.org\/10.1007\/s40747-025-01852-6","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"value":"2199-4536","type":"print"},{"value":"2198-6053","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"20 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors assert that there are no Conflict of interest in relation to the publication of this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"267"}}