{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T05:14:06Z","timestamp":1726463646124},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2020,5,4]],"date-time":"2020-05-04T00:00:00Z","timestamp":1588550400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,5,4]],"date-time":"2020-05-04T00:00:00Z","timestamp":1588550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61673179"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2020,11]]},"DOI":"10.1007\/s13042-020-01130-6","type":"journal-article","created":{"date-parts":[[2020,5,4]],"date-time":"2020-05-04T14:03:57Z","timestamp":1588601037000},"page":"2461-2474","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Attentive multi-view reinforcement learning"],"prefix":"10.1007","volume":"11","author":[{"given":"Yueyue","family":"Hu","sequence":"first","affiliation":[]},{"given":"Shiliang","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Jing","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,5,4]]},"reference":[{"key":"1130_CR1","unstructured":"Ba J, Mnih V, Kavukcuoglu K (2014) Multiple object recognition with visual attention. arXiv:1412.7755"},{"key":"1130_CR2","unstructured":"Barati E, Chen X, Zhong Z (2019) Attention-based deep reinforcement learning for multi-view environments. In: Proceedings of the 18th international conference on autonomous agents and multiagent systems, pp 1805\u20131807"},{"key":"1130_CR3","unstructured":"Barreto A, Borsa D, Quan J, Schaul T, Silver D, Hessel M, Mankowitz D, \u017d\u00eddek A, Munos R (2019) Transfer in deep reinforcement learning using successor features and generalised policy improvement. arXiv:1901.10964"},{"key":"1130_CR4","unstructured":"Barreto A, Dabney W, Munos R, Hunt JJ, Schaul T, van Hasselt HP, Silver D (2017). Successor features for transfer in reinforcement learning. In: Advances in neural information processing systems, pp 4055\u20134065"},{"key":"1130_CR5","doi-asserted-by":"crossref","unstructured":"Chen X, Ma H, Wan J, Li B, Xia T (2017) Multi-view 3D object detection network for autonomous driving. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1907\u20131915","DOI":"10.1109\/CVPR.2017.691"},{"key":"1130_CR6","unstructured":"Durugkar I, Gemp I, Mahadevan S (2016) Generative multi-adversarial networks. arXiv:1611.01673"},{"key":"1130_CR7","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge"},{"key":"1130_CR8","unstructured":"Hausknecht M, Stone P (2015) Deep recurrent q-learning for partially observable MDPS. In: 2015 AAAI Fall Symposium Series"},{"key":"1130_CR9","unstructured":"Hu Y, Sun S, Xu X, Zhao J (2019) Multi-view deep attention network for reinforcement learning. In: 34th AAAI Conference on Artificial Intelligence, pp 1\u20132"},{"key":"1130_CR10","unstructured":"Iwata T, Yamada M (2016) Multi-view anomaly detection via robust probabilistic latent variable models. In: Advances in neural information processing systems, pp 1136\u20131144"},{"key":"1130_CR11","unstructured":"Jiang J, Lu Z (2018) Learning attentional communication for multi-agent cooperation. In: Advances in neural information processing systems, pp 7254\u20137264"},{"key":"1130_CR12","doi-asserted-by":"crossref","unstructured":"Karpathy A, Fei-Fei L (2015) Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3128\u20133137","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"1130_CR13","unstructured":"Kulkarni TD, Narasimhan K, Saeedi A, Tenenbaum J (2016) Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation. In: Advances in neural information processing systems, pp 3675\u20133683"},{"issue":"7553","key":"1130_CR14","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"issue":"1","key":"1130_CR15","first-page":"1334","volume":"17","author":"S Levine","year":"2016","unstructured":"Levine S, Finn C, Darrell T, Abbeel P (2016) End-to-end training of deep visuomotor policies. J Mach Learn Res 17(1):1334\u20131373","journal-title":"J Mach Learn Res"},{"key":"1130_CR16","unstructured":"Li M, Wu L, Ammar HB, Wang J (2019) Multi-view reinforcement learning. In: Advances in neural information processing systems"},{"issue":"10","key":"1130_CR17","doi-asserted-by":"publisher","first-page":"1863","DOI":"10.1109\/TKDE.2018.2872063","volume":"31","author":"Y Li","year":"2018","unstructured":"Li Y, Yang M, Zhang ZM (2018) A survey of multi-view representation learning. IEEE Trans Knowl Data Eng 31(10):1863\u20131883","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1130_CR18","unstructured":"Lowe R, Wu Y, Tamar A, Harb J, Abbeel OP, Mordatch I (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in neural information processing systems, pp 6379\u20136390"},{"key":"1130_CR19","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Graves A, Antonoglou I, Wierstra D, Riedmiller M (2013) Playing atari with deep reinforcement learning. arXiv:1312.5602"},{"issue":"7540","key":"1130_CR20","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, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"1130_CR21","unstructured":"Nie W, Narodytska N, Patel A (2018) Relgan: relational generative adversarial networks for text generation. In: International conference on learning representations"},{"key":"1130_CR22","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2015) Prioritized experience replay. arXiv:1511.05952"},{"issue":"7587","key":"1130_CR23","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van Den Driessche G, Schrittwieser J, Antonoglou I, Panneershelvam V, Lanctot M et al (2016) Mastering the game of go with deep neural networks and tree search. Nature 529(7587):484\u2013489","journal-title":"Nature"},{"key":"1130_CR24","unstructured":"Silver D, Newnham L, Barker D, Weller S, McFall J (2013) Concurrent reinforcement learning from customer interactions. In: International conference on machine learning, pp 924\u2013932"},{"issue":"7676","key":"1130_CR25","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver D, Schrittwieser J, Simonyan K, Antonoglou I, Huang A, Guez A, Hubert T, Baker L, Lai M, Bolton A et al (2017) Mastering the game of go without human knowledge. Nature 550(7676):354\u2013359","journal-title":"Nature"},{"key":"1130_CR26","unstructured":"Sorokin I, Seleznev A, Pavlov M, Fedorov A, Ignateva A (2015) Deep attention recurrent q-network. arXiv:1512.01693"},{"key":"1130_CR27","doi-asserted-by":"crossref","unstructured":"Su H, Maji S, Kalogerakis E, Learned-Miller E (2015) Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings of the IEEE international conference on computer vision, pp 945\u2013953","DOI":"10.1109\/ICCV.2015.114"},{"issue":"7\u20138","key":"1130_CR28","doi-asserted-by":"publisher","first-page":"2031","DOI":"10.1007\/s00521-013-1362-6","volume":"23","author":"S Sun","year":"2013","unstructured":"Sun S (2013) A survey of multi-view machine learning. Neural Comput Appl 23(7\u20138):2031\u20132038","journal-title":"Neural Comput Appl"},{"key":"1130_CR29","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton RS, Barto AG (2018) Reinforcement learning: an introduction. MIT Press, Cambridge"},{"key":"1130_CR30","unstructured":"Sutton RS, McAllester DA, Singh SP, Mansour Y (2000) Policy gradient methods for reinforcement learning with function approximation. In: Advances in neural information processing systems, pp 1057\u20131063"},{"key":"1130_CR31","doi-asserted-by":"crossref","unstructured":"Van\u00a0Hasselt H, Guez A, Silver, D (2016) Deep reinforcement learning with double q-learning. In: Thirtieth AAAI conference on artificial intelligence, pp 2613\u20132621","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"1130_CR32","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals O, Babuschkin I, Czarnecki WM, Mathieu M, Dudzik A, Chung J, Choi DH, Powell R, Ewalds T, Georgiev P et al (2019) Grandmaster level in starcraft II using multi-agent reinforcement learning. Nature 575:350\u2013354","journal-title":"Nature"},{"key":"1130_CR33","unstructured":"Wang W, Arora R, Livescu K, Bilmes J (2015) On deep multi-view representation learning. In: International conference on machine learning, pp 1083\u20131092"},{"key":"1130_CR34","unstructured":"Wang Z, Schaul T, Hessel M, Van\u00a0Hasselt H, Lanctot M, De\u00a0Freitas N (2015) Dueling network architectures for deep reinforcement learning. arXiv:1511.06581"},{"key":"1130_CR35","unstructured":"Watter M, Springenberg J, Boedecker J, Riedmiller M (2015) Embed to control: a locally linear latent dynamics model for control from raw images. In: Advances in neural information processing systems, pp 2746\u20132754"},{"issue":"3\u20134","key":"1130_CR36","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams RJ (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach Learn 8(3\u20134):229\u2013256","journal-title":"Mach Learn"},{"key":"1130_CR37","unstructured":"Willianms R (1988) Toward a theory of reinforcement-learning connectionist systems. Technical Report NU-CCS-88-3, Northeastern University"},{"key":"1130_CR38","unstructured":"Zawadzki E, Lipson A, Leyton-Brown K (2014) Empirically evaluating multiagent learning algorithms. arXiv:1401.8074"},{"key":"1130_CR39","doi-asserted-by":"crossref","unstructured":"Zhao B, Wu X, Cheng ZQ, Liu H, Jie Z, Feng J (2018) Multi-view image generation from a single-view. In: 2018 ACM multimedia conference on multimedia conference, pp 383\u2013391","DOI":"10.1145\/3240508.3240536"},{"key":"1130_CR40","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.inffus.2017.02.007","volume":"38","author":"J Zhao","year":"2017","unstructured":"Zhao J, Xie X, Xu X, Sun S (2017) Multi-view learning overview: recent progress and new challenges. Inf Fusion 38:43\u201354","journal-title":"Inf Fusion"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-020-01130-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-020-01130-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-020-01130-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:22:31Z","timestamp":1666484551000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-020-01130-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,4]]},"references-count":40,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2020,11]]}},"alternative-id":["1130"],"URL":"https:\/\/doi.org\/10.1007\/s13042-020-01130-6","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,5,4]]},"assertion":[{"value":"28 November 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 April 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}