{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T16:04:57Z","timestamp":1760889897669,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":41,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,7,5]],"date-time":"2019-07-05T00:00:00Z","timestamp":1562284800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Scientific Research Foundation of Science and Technology Department of Hubei Province","award":["2018CFB276"],"award-info":[{"award-number":["2018CFB276"]}]},{"name":"Scientific and Technological Research of Education Department of Hubei Province","award":["Q20181408"],"award-info":[{"award-number":["Q20181408"]}]},{"name":"Doctor Launching Fund of Hubei University of Technology","award":["BSQD20160004"],"award-info":[{"award-number":["BSQD20160004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,7,5]]},"DOI":"10.1145\/3342999.3343012","type":"proceedings-article","created":{"date-parts":[[2019,8,9]],"date-time":"2019-08-09T12:21:03Z","timestamp":1565353263000},"page":"38-41","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["A Priority Experience Replay Sampling Method Based on Upper Confidence Bound"],"prefix":"10.1145","author":[{"given":"Fengkai","family":"Ke","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Hubei University of Technology, China"}]},{"given":"Daxing","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Hubei University of Technology, China"}]},{"given":"Guodong","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Hubei University of Technology, China"}]},{"given":"Wei","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Hubei University of Technology, China"}]}],"member":"320","published-online":{"date-parts":[[2019,7,5]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2008.917757"},{"volume-title":"Acceleration techniques for GPU-based","author":"Kruger J","key":"e_1_3_2_1_2_1","unstructured":"Kruger J , Westermann R. Acceleration techniques for GPU-based volume rendering{C}\/\/ Visualization, Vis. 2003 . Kruger J, Westermann R. Acceleration techniques for GPU-based volume rendering{C}\/\/ Visualization, Vis. 2003."},{"key":"e_1_3_2_1_3_1","volume-title":"DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment{J}","author":"Chang L","year":"2016","unstructured":"Chang L , Yu C , Yan L , DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment{J} . 2016 . Chang L, Yu C, Yan L, et al. DeepFood: Deep Learning-Based Food Image Recognition for Computer-Aided Dietary Assessment{J}. 2016."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.08.050"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2741510"},{"key":"e_1_3_2_1_6_1","volume-title":"Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction{J}","author":"Dai Q","year":"2018","unstructured":"Dai Q , Chopp H , Pouyet E , Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction{J} . 2018 . Dai Q, Chopp H, Pouyet E, et al. Adaptive Image Sampling using Deep Learning and its Application on X-Ray Fluorescence Image Reconstruction{J}. 2018."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.106218"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806222"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-018-0548-3"},{"key":"e_1_3_2_1_11_1","volume-title":"Theory of the backpropagation neural network{C}\/\/ International Joint Conference on Neural Networks","author":"Hecht-Nielsen","year":"2002","unstructured":"Hecht-Nielsen . Theory of the backpropagation neural network{C}\/\/ International Joint Conference on Neural Networks . 2002 . Hecht-Nielsen. Theory of the backpropagation neural network{C}\/\/ International Joint Conference on Neural Networks. 2002."},{"issue":"7","key":"e_1_3_2_1_12_1","first-page":"38","article-title":"Distilling the Knowledge in a Neural Network{J}","volume":"14","author":"Hinton G","year":"2015","unstructured":"Hinton G , Vinyals O , Dean J . Distilling the Knowledge in a Neural Network{J} . Computer Science , 2015 , 14 ( 7 ): 38 -- 39 . Hinton G, Vinyals O, Dean J. Distilling the Knowledge in a Neural Network{J}. Computer Science, 2015, 14(7):38--39.","journal-title":"Computer Science"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/12.106218"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.554195"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0925-2312(01)00702-0"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(02)00963-7"},{"key":"e_1_3_2_1_18_1","first-page":"330","article-title":"Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents{J}","volume":"1993","author":"Tan M","unstructured":"Tan M . Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents{J} . Machine Learning Proceedings , 1993 : 330 -- 337 . Tan M. Multi-Agent Reinforcement Learning: Independent vs. Cooperative Agents{J}. Machine Learning Proceedings, 1993:330--337.","journal-title":"Machine Learning Proceedings"},{"issue":"10","key":"e_1_3_2_1_19_1","first-page":"1633","article-title":"Transfer Learning for Reinforcement Learning Domains: A Survey{J}","volume":"10","author":"Taylor M E","year":"2009","unstructured":"Taylor M E , Stone P . Transfer Learning for Reinforcement Learning Domains: A Survey{J} . Journal of Machine Learning Research , 2009 , 10 ( 10 ): 1633 -- 1685 . Taylor M E, Stone P. Transfer Learning for Reinforcement Learning Domains: A Survey{J}. Journal of Machine Learning Research, 2009, 10(10):1633--1685.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"e_1_3_2_1_21_1","volume-title":"One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay{J}","author":"Bruce J","year":"2017","unstructured":"Bruce J , Suenderhauf N , Mirowski P , One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay{J} . 2017 . Bruce J, Suenderhauf N, Mirowski P, et al. One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay{J}. 2017."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790981"},{"issue":"3","key":"e_1_3_2_1_23_1","first-page":"274","article-title":"Experience Replay for Least-Squares Policy Iteration{J}","volume":"1","author":"Quan","year":"2015","unstructured":"Quan , Zhou, Qiming , et al. Experience Replay for Least-Squares Policy Iteration{J} . IEEE\/CAA Journal of Automatica Sinica , 2015 , 1 ( 3 ): 274 -- 281 . Quan, Zhou, Qiming, et al. Experience Replay for Least-Squares Policy Iteration{J}. IEEE\/CAA Journal of Automatica Sinica, 2015, 1(3):274--281.","journal-title":"IEEE\/CAA Journal of Automatica Sinica"},{"key":"e_1_3_2_1_24_1","volume-title":"Using a Deep Reinforcement Learning Agent for Traffic Signal Control{J}","author":"Genders W","year":"2016","unstructured":"Genders W , Razavi S. Using a Deep Reinforcement Learning Agent for Traffic Signal Control{J} . 2016 . Genders W, Razavi S. Using a Deep Reinforcement Learning Agent for Traffic Signal Control{J}. 2016."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2012.63"},{"key":"e_1_3_2_1_26_1","volume-title":"Experience Replay for Continual Learning{J}","author":"Rolnick D","year":"2018","unstructured":"Rolnick D , Ahuja A , Schwarz J , Experience Replay for Continual Learning{J} . 2018 . Rolnick D, Ahuja A, Schwarz J, et al. Experience Replay for Continual Learning{J}. 2018."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622737.1622748"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"e_1_3_2_1_30_1","volume-title":"Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning{J}","author":"Foerster J","year":"2017","unstructured":"Foerster J , Nardelli N , Farquhar G , Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning{J} . 2017 . Foerster J, Nardelli N, Farquhar G, et al. Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning{J}. 2017."},{"key":"e_1_3_2_1_31_1","volume-title":"Sample Efficient Actor-Critic with Experience Replay{J}","author":"Wang Z","year":"2016","unstructured":"Wang Z , Bapst V , Heess N , Sample Efficient Actor-Critic with Experience Replay{J} . 2016 . Wang Z, Bapst V, Heess N, et al. Sample Efficient Actor-Critic with Experience Replay{J}. 2016."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2488680"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2013.09.043"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"e_1_3_2_1_35_1","volume-title":"Distributed Prioritized Experience Replay{J}","author":"Horgan D","year":"2018","unstructured":"Horgan D , Quan J , Budden D , Distributed Prioritized Experience Replay{J} . 2018 . Horgan D, Quan J, Budden D, et al. Distributed Prioritized Experience Replay{J}. 2018."},{"key":"e_1_3_2_1_36_1","volume-title":"Q-learning with experience replay in a dynamic environment{C}\/\/ Computational Intelligence","author":"Pieters M","year":"2017","unstructured":"Pieters M , Wiering M A . Q-learning with experience replay in a dynamic environment{C}\/\/ Computational Intelligence . 2017 . Pieters M, Wiering M A. Q-learning with experience replay in a dynamic environment{C}\/\/ Computational Intelligence. 2017."},{"key":"e_1_3_2_1_37_1","volume-title":"Multi-Batch Experience Replay for Fast Convergence of Continuous Action Control{J}","author":"Han S","year":"2017","unstructured":"Han S , Sung Y. Multi-Batch Experience Replay for Fast Convergence of Continuous Action Control{J} . 2017 . Han S, Sung Y. Multi-Batch Experience Replay for Fast Convergence of Continuous Action Control{J}. 2017."},{"key":"e_1_3_2_1_38_1","volume-title":"Double-Q Learning, & Snapshot Ensembling{J}.","author":"Schulze C","year":"2018","unstructured":"Schulze C , Schulze M. ViZDoom: DRQN with Prioritized Experience Replay , Double-Q Learning, & Snapshot Ensembling{J}. 2018 . Schulze C, Schulze M. ViZDoom: DRQN with Prioritized Experience Replay, Double-Q Learning, & Snapshot Ensembling{J}. 2018."},{"key":"e_1_3_2_1_39_1","volume-title":"The research of algorithms and architectures on deep Q-network{D}","author":"Zhai Jianwei","year":"2017","unstructured":"Zhai Jianwei . The research of algorithms and architectures on deep Q-network{D} . 2017 . Zhai Jianwei. The research of algorithms and architectures on deep Q-network{D}. 2017."},{"key":"e_1_3_2_1_40_1","volume-title":"Impact of experience replay with fixed history length on Q-learning. Computer Engineering{J}","author":"Lin M","year":"2006","unstructured":"Lin M , Zhu J , Sun Z. Impact of experience replay with fixed history length on Q-learning. Computer Engineering{J} , 2006 , 32(6):7--10. Lin M, Zhu J, Sun Z. Impact of experience replay with fixed history length on Q-learning. Computer Engineering{J}, 2006, 32(6):7--10."},{"key":"e_1_3_2_1_41_1","volume-title":"A deep Q-network method based on upper confidence bound experience sampling. Journal of Computer Research and Development{J}","author":"Zhu F","year":"2018","unstructured":"Zhu F , Wu W , , A deep Q-network method based on upper confidence bound experience sampling. Journal of Computer Research and Development{J} . 2018 , v.55(08):100--111 Zhu F, Wu W, et al., A deep Q-network method based on upper confidence bound experience sampling. Journal of Computer Research and Development{J}. 2018, v.55(08):100--111"}],"event":{"name":"ICDLT 2019: 2019 3rd International Conference on Deep Learning Technologies","sponsor":["Nanyang Technological University","Chongqing University of Posts and Telecommunications"],"location":"Xiamen China","acronym":"ICDLT 2019"},"container-title":["Proceedings of the 2019 3rd International Conference on Deep Learning Technologies"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3342999.3343012","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3342999.3343012","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:23:02Z","timestamp":1750202582000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3342999.3343012"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,5]]},"references-count":41,"alternative-id":["10.1145\/3342999.3343012","10.1145\/3342999"],"URL":"https:\/\/doi.org\/10.1145\/3342999.3343012","relation":{},"subject":[],"published":{"date-parts":[[2019,7,5]]},"assertion":[{"value":"2019-07-05","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}