{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:51:00Z","timestamp":1774453860139,"version":"3.50.1"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61202445"],"award-info":[{"award-number":["61202445"]}],"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":["61472064"],"award-info":[{"award-number":["61472064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3037940","type":"journal-article","created":{"date-parts":[[2020,11,13]],"date-time":"2020-11-13T16:18:43Z","timestamp":1605284323000},"page":"213587-213601","source":"Crossref","is-referenced-by-count":17,"title":["A Dynamic Bidding Strategy Based on Model-Free Reinforcement Learning in Display Advertising"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3679-7915","authenticated-orcid":false,"given":"Mengjuan","family":"Liu","sequence":"first","affiliation":[{"name":"Network and Data Security Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3074-5383","authenticated-orcid":false,"given":"Li","family":"Jiaxing","sequence":"additional","affiliation":[{"name":"Network and Data Security Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1354-2197","authenticated-orcid":false,"given":"Zhengning","family":"Hu","sequence":"additional","affiliation":[{"name":"Network and Data Security Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5428-625X","authenticated-orcid":false,"given":"Jinyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Network and Data Security Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2868-0442","authenticated-orcid":false,"given":"Xuyun","family":"Nie","sequence":"additional","affiliation":[{"name":"Network and Data Security Key Laboratory of Sichuan Province, University of Electronic Science and Technology of China, Chengdu, China"}]}],"member":"263","reference":[{"key":"ref31","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"loffe","year":"2015","journal-title":"Proc ICML"},{"key":"ref30","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume":"14","author":"glorot","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783269"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623633"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992695"},{"key":"ref14","article-title":"Artificial intelligence: Foundations of computational agents","author":"david","year":"2011","journal-title":"Artificial Intelligence"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271748"},{"key":"ref16","first-page":"2587","article-title":"Addressing Function Approximation Error in Actor-Critic Methods","author":"fujimoto","year":"2018","journal-title":"Proc ICML"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/2339530.2339655"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2970463"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2648584.2648590"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2684822.2697041"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"1291","DOI":"10.1109\/TSMCC.2012.2218595","article-title":"A survey of actor-critic reinforcement learning: Standard and natural policy gradients","volume":"42","author":"ivo","year":"2012","journal-title":"IEEE Trans Syst Man Cybern C (Appl Rev )"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1561\/9781680833119"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242643"},{"key":"ref29","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124761"},{"key":"ref8","first-page":"45","article-title":"Deep learning over multi-field categorical data: a case study on user response prediction","author":"zhang","year":"2016","journal-title":"Proc ECIR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/2168752.2168771"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2501040.2501980"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SOLI.2014.6960761"},{"key":"ref1","first-page":"651","article-title":"Lift-based bidding in ad selection","author":"xu","year":"2016","journal-title":"Proc AAAI"},{"key":"ref20","first-page":"711","author":"du","year":"2017","journal-title":"Improving Real-Time Bidding Using a Constrained Markov Decision Process"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219918"},{"key":"ref21","first-page":"645","article-title":"Reinforcement learning for MDPs with constraints","author":"perter","year":"2006","journal-title":"Proc ECML"},{"key":"ref24","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"ref25","article-title":"Continuous control with deep reinforcement learning","author":"lillicpap","year":"2016","journal-title":"Proc ICLR"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09258910.pdf?arnumber=9258910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T18:29:43Z","timestamp":1764095383000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9258910\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3037940","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]}}}