{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T05:47:02Z","timestamp":1776404822747,"version":"3.51.2"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T00:00:00Z","timestamp":1536278400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"This work is supported by the Fundamental Research Funds for the Central Universi-ties","award":["2017XKZD03"],"award-info":[{"award-number":["2017XKZD03"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2019,2]]},"DOI":"10.1007\/s10489-018-1296-x","type":"journal-article","created":{"date-parts":[[2018,9,7]],"date-time":"2018-09-07T04:01:19Z","timestamp":1536292879000},"page":"581-591","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":32,"title":["Applications of asynchronous deep reinforcement learning based on dynamic updating weights"],"prefix":"10.1007","volume":"49","author":[{"given":"Xingyu","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shifei","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexuan","family":"An","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weikuan","family":"Jia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,7]]},"reference":[{"key":"1296_CR1","doi-asserted-by":"crossref","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press","DOI":"10.1016\/S1474-6670(17)38315-5"},{"key":"1296_CR2","unstructured":"Mnih V, Kavukcuoglu K, Silver D et al (2013) Playing atari with deep reinforcement learning. In: Proceedings of workshops at the 26th neural information processing systems 2013. Lake Tahoe, USA, pp 201\u2013220"},{"issue":"39","key":"1296_CR3","first-page":"1","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine S, Finn C, Darrell T et al (2016) End-to-end training of deep visuomotor policies. J Mach Learn Res 17(39):1\u201340","journal-title":"J Mach Learn Res"},{"key":"1296_CR4","doi-asserted-by":"crossref","unstructured":"Zhang M, Mccarthy Z, Finn C, et al (2016) Learning deep neural network policies with continuous memory states. In: Proceedings of the international conference on robotics and automation. Stockholm, Sweden, pp 520\u2013527","DOI":"10.1109\/ICRA.2016.7487174"},{"key":"1296_CR5","unstructured":"Satija H, Pineau J (2016) Simultaneous machine translation using deep reinforcement learning. In: Proceedings of the workshops of international conference on machine learning. New York, USA, pp 110\u2013119"},{"key":"1296_CR6","unstructured":"Oh J, Guo X, Lee H et al (2015) Action-conditional video prediction using deep networks in atari games. In: Advances in neural information processing systems, pp 2863\u20132871"},{"key":"1296_CR7","doi-asserted-by":"crossref","unstructured":"Li J, Monroe W, Ritter A et al (2016) Deep reinforcement learning for dialogue generation. In: Proceedings of the conference on empirical methods in natural language processing. Austin, USA, pp 1192\u20131202","DOI":"10.18653\/v1\/D16-1127"},{"key":"1296_CR8","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023","volume":"19","author":"A Sallab","year":"2017","unstructured":"Sallab A, Abdou M, Perot E et al (2017) Deep reinforcement learning framework for autonomous driving. Electron Imag 19:70\u201376","journal-title":"Electron Imag"},{"key":"1296_CR9","doi-asserted-by":"crossref","unstructured":"Caicedo J, Lazebnik S (2015) Active object localization with deep reinforcement learning. In: IEEE international conference on computer vision. IEEE, pp 2488\u20132496","DOI":"10.1109\/ICCV.2015.286"},{"issue":"7587","key":"1296_CR10","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ et al (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"issue":"7676","key":"1296_CR11","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver D, Schrittwieser J, Simonyan K et al (2017) Mastering the game of Go without human knowledge. Nature 550(7676):354\u2013359","journal-title":"Nature"},{"issue":"7540","key":"1296_CR12","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, et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540): 529\u2013533","journal-title":"Nature"},{"key":"1296_CR13","doi-asserted-by":"crossref","unstructured":"Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double Q-Learning. AAAI, pp 2094\u20132100","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"1296_CR14","unstructured":"Wang Z, Freitas N, Lanctot M (2016) Dueling network architectures for deep reinforcement learning. In: Proceedings of the international conference on machine learning. New York, USA, pp 1995\u20132003"},{"key":"1296_CR15","unstructured":"Schaul T, Quan J, Antonoglou I et al (2016) Prioritized experience replay. In: Proceedings of the 4th international conference on learning representations. San Juan, Puerto Rico, pp 322\u2013355"},{"key":"1296_CR16","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A et al (2015) Continuous control with deep reinforcement learning. arXiv: 1509.02971"},{"key":"1296_CR17","unstructured":"Silver D, Lever G, Heess N et al (2014) Deterministic policy gradient algorithms. In: Proceedings of the 31st international conference on machine learning, pp 387\u2013395"},{"key":"1296_CR18","unstructured":"Konda V, Tsitsiklis J (2000) Actor-critic algorithms3 advances in neural information processing systems, pp 1008\u20131014"},{"key":"1296_CR19","unstructured":"Mnih V, Badia A, Mirza M et al (2016) Asynchronous methods for deep reinforcement learning. In: International conference on machine learning, pp 1928\u20131937"},{"issue":"4","key":"1296_CR20","first-page":"233","volume":"15","author":"CJCH Watkins","year":"1989","unstructured":"Watkins CJCH (1989) Learning from delayed rewards. Robot Auton Syst 15(4):233\u2013235","journal-title":"Robot Auton Syst"},{"issue":"2","key":"1296_CR21","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1007\/s13042-015-0351-8","volume":"8","author":"S Ding","year":"2017","unstructured":"Ding S, Zhang N, Zhang J et al (2017) Unsupervised extreme learning machine with representational features. Int J Mach Learn Cybern 8(2):587\u2013595","journal-title":"Int J Mach Learn Cybern"},{"issue":"7","key":"1296_CR22","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1007\/s00521-015-2009-6","volume":"27","author":"H Liao","year":"2016","unstructured":"Liao H, Ding S, Wang M et al (2016) An overview on rough neural networks. Neural Comput Appl 27(7):1805\u20131816","journal-title":"Neural Comput Appl"},{"key":"1296_CR23","unstructured":"Schulman J, Moritz P, Levine S et al (2015) High-dimensional continuous control using generalized advantage estimation. arXiv: 1506.02438"},{"key":"1296_CR24","unstructured":"Tieleman T, Hinton G (2012) Lecture 6.5-rmsprop: divide the gradient by a running average of its recent magnitude. In: COURSERA: neural networks for machine learning, p 4"},{"key":"1296_CR25","unstructured":"Kingma DP, Ba J (2014) Adam A method for stochastic optimization. arXiv: 1412.6980"},{"issue":"4","key":"1296_CR26","doi-asserted-by":"publisher","first-page":"993","DOI":"10.1007\/s10489-017-0988-y","volume":"47","author":"LA Ferreira","year":"2017","unstructured":"Ferreira LA, Bianchi RAC, Santos PE et al (2017) Answer set programming for non-stationary Markov decision processes. Appl Intell 47(4):993\u20131007","journal-title":"Appl Intell"},{"issue":"3","key":"1296_CR27","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/s10489-015-0665-y","volume":"43","author":"E Pakizeh","year":"2015","unstructured":"Pakizeh E, Pedram MM, Palhang M (2015) Multi-criteria expertness based cooperative method for SARSA and eligibility trace algorithms. Appl Intell 43(3):487\u2013498","journal-title":"Appl Intell"},{"key":"1296_CR28","unstructured":"Hessel M, Modayil J, Van Hasselt H et al (2017) Rainbow: combining improvements in deep reinforcement learning. arXiv: 1710.02298"},{"issue":"2","key":"1296_CR29","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/s10489-012-0412-6","volume":"39","author":"NA Vien","year":"2013","unstructured":"Vien NA, Ertel W, Chung TC (2013) Learning via human feedback in continuous state and action spaces. Appl Intell 39(2):267\u2013278","journal-title":"Appl Intell"},{"key":"1296_CR30","unstructured":"Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 315\u2013323"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10489-018-1296-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-018-1296-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-018-1296-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T22:53:10Z","timestamp":1693867990000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10489-018-1296-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,7]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,2]]}},"alternative-id":["1296"],"URL":"https:\/\/doi.org\/10.1007\/s10489-018-1296-x","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9,7]]},"assertion":[{"value":"7 September 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}