{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T13:30:10Z","timestamp":1742995810242,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030041816"},{"type":"electronic","value":"9783030041823"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-030-04182-3_27","type":"book-chapter","created":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T10:19:48Z","timestamp":1542449988000},"page":"303-312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Accelerating Spatio-Temporal Deep Reinforcement Learning Model for Game Strategy"],"prefix":"10.1007","author":[{"given":"Yifan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchun","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,18]]},"reference":[{"key":"27_CR1","unstructured":"Vinyals, O., et al.: StarCraft II: A New Challenge for Reinforcement Learning. https:\/\/arxiv.org\/abs\/1708.04782. Accessed 16 Aug 2017"},{"issue":"6","key":"27_CR2","first-page":"1349","volume":"20","author":"K Yu","year":"2013","unstructured":"Yu, K., Jia, L., Chen, Y., Xu, W.: Deep learning: yesterday, today, and tomorrow. J. Comput. Res. Develop. 20(6), 1349 (2013)","journal-title":"J. Comput. Res. Develop."},{"key":"27_CR3","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: International Conference on Neural Information Processing Systems, pp. 1097\u20131105. Curran Associates Inc. (2012)"},{"issue":"3","key":"27_CR4","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vis."},{"key":"27_CR5","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Li, F.F.: Large-scale video classification with convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732. IEEE Computer Society (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"27_CR6","doi-asserted-by":"crossref","unstructured":"Cho, K., Merrienboer, B.V., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., Bengio, Y.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, pp. 1724\u20131734 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"issue":"9","key":"27_CR7","first-page":"184","volume":"35","author":"Z Yang","year":"2014","unstructured":"Yang, Z., Tao, D.P., Zhang, S.Y., Jin, L.W.: Similar handwritten Chinese character recognition based on deep neural networks with big data. J. Commun. 35(9), 184\u2013189 (2014)","journal-title":"J. Commun."},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"issue":"9","key":"27_CR9","first-page":"1936","volume":"51","author":"Y Li","year":"2014","unstructured":"Li, Y., Zhang, J., Pan, D., Hu, D.: A study of speech recognition based on RNN-RBM language model. J. Comput. Res. Develop. 51(9), 1936\u20131944 (2014)","journal-title":"J. Comput. Res. Develop."},{"issue":"8","key":"27_CR10","first-page":"2806","volume":"29","author":"ZJ Sun","year":"2012","unstructured":"Sun, Z.J., Xue, L., Xu, Y.M., Wang, Z.: Overview of deep learning. Appl. Res. Comput. 29(8), 2806\u20132810 (2012)","journal-title":"Appl. Res. Comput."},{"key":"27_CR11","volume-title":"Reinforcement Learning: An Introduction, Bradford Book","author":"RS Sutton","year":"2005","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, Bradford Book. MIT Press, Cambridge (2005). IEEE Transactions on Neural Networks 16(1), 285\u2013286"},{"issue":"11","key":"27_CR12","doi-asserted-by":"publisher","first-page":"1238","DOI":"10.1177\/0278364913495721","volume":"32","author":"J Kober","year":"2013","unstructured":"Kober, J., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238\u20131274 (2013)","journal-title":"Int. J. Robot. Res."},{"issue":"2","key":"27_CR13","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G Tesauro","year":"1989","unstructured":"Tesauro, G.: TD-Gammon, a self-teaching backgammon program, achieves master-level play. Neural Comput. 6(2), 215\u2013219 (1989)","journal-title":"Neural Comput."},{"key":"27_CR14","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1007\/11871842_29","volume-title":"Machine Learning: ECML 2006","author":"L Kocsis","year":"2006","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based Monte-Carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282\u2013293. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11871842_29"},{"issue":"3","key":"27_CR15","first-page":"677","volume":"37","author":"QM Fu","year":"2014","unstructured":"Fu, Q.M., Liu, Q., Wang, H., Xiao, F., Yu, J., Li, J.: A novel off policy Q(\u03bb) algorithm based on linear function approximation. Chin. J. Comput. 37(3), 677\u2013686 (2014)","journal-title":"Chin. J. Comput."},{"issue":"8","key":"27_CR16","first-page":"1372","volume":"30","author":"Y Gao","year":"2007","unstructured":"Gao, Y., Zhou, R.Y., Wang, H., Cao, Z.X.: Study on an average reward reinforcement learning algorithm. Chin. J. Comput. 30(8), 1372\u20131378 (2007)","journal-title":"Chin. J. Comput."},{"issue":"5","key":"27_CR17","first-page":"765","volume":"31","author":"YZ Wei","year":"2005","unstructured":"Wei, Y.Z., Zhao, M.Y.: A reinforcement learning-based approach to dynamic job-shop scheduling. Acta Autom. Sin. 31(5), 765\u2013771 (2005)","journal-title":"Acta Autom. Sin."},{"key":"27_CR18","doi-asserted-by":"crossref","unstructured":"Ipek, E., Mutlu, O., Carunana, R.: Self-optimizing memory controllers: a reinforcement learning approach. In: International Symposium on Computer Architecture, pp. 39\u201350. IEEE (2008)","DOI":"10.1145\/1394608.1382172"},{"key":"27_CR19","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. Computer Science, pp. 201\u2013220 (2013)"},{"issue":"7540","key":"27_CR20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"7587","key":"27_CR21","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"27_CR22","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R., Singh, S.: Action-conditional video prediction using deep networks in atari games. In: Proceedings of the Neural Information Processing Systems, Montreal, Canada, pp. 2863\u20132871 (2015)"},{"key":"27_CR23","doi-asserted-by":"crossref","unstructured":"Caicedo, J.C., Lazebnik, S.: Active object localization with deep reinforcement learning. In: IEEE International Conference on Computer Vision, pp. 2488\u20132496. IEEE Computer Society (2015)","DOI":"10.1109\/ICCV.2015.286"},{"issue":"6","key":"27_CR24","first-page":"A187","volume":"8","author":"TP Lillicrap","year":"2016","unstructured":"Lillicrap, T.P.: Continuous control with deep reinforcement learning. Comput. Sci. 8(6), A187 (2016)","journal-title":"Comput. Sci."},{"key":"27_CR25","unstructured":"Duan, Y., Chen, X., Houthooft, R., Schulman, J., Abbeel, P.: Benchmarking deep reinforcement learning for continuous control, pp. 1329\u20131338 (2016)"},{"key":"27_CR26","unstructured":"Gu, S., Lillicrap, T., Sutskever, I., Levine, S.: Continuous deep Q-Learning with model-based acceleration. In: Proceeding of ICML 2016 Proceedings of the 33rd International Conference on International Conference on Machine Learning, vol. 48, pp. 2829\u20132838 (2016)"},{"key":"27_CR27","unstructured":"Hansen, S.: Using deep Q-learning to control optimization hyperparameters. https:\/\/arxiv.org\/abs\/1602.04062v2. Accessed 19 Jun 2016"},{"key":"27_CR28","unstructured":"Andrychowicz, M.: Learning to learn by gradient descent by gradient descent. In: Proceedings of the Conference on Neural Information Processing Systems, Barcelona, Spain, pp. 3981\u20133989 (2016)"},{"key":"27_CR29","unstructured":"Mnih, V.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the International Conference on Machine Learning, New York, USA, pp. 1928\u20131937 (2016)"},{"key":"27_CR30","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal Policy Optimization Algorithms. https:\/\/arxiv.org\/abs\/1707.06347v2. Accessed 28 Aug 2017"},{"key":"27_CR31","unstructured":"Schulman, J., Levine, S., Moritz, P., Jordan, M.I., Abbeel, P.: Trust Region Policy Optimization. Computer Science, pp. 1889\u20131897 (2015)"},{"key":"27_CR32","unstructured":"Howard, A.G., et al.: MobileNets: efficient convolutional neural networks for mobile vision applications. https:\/\/arxiv.org\/abs\/1704.04861. Accessed 17 Apr 2017"},{"key":"27_CR33","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W., Woo, W.: Convolutional LSTM Network: a machine learning approach for precipitation nowcasting. In: International Conference on Neural Information Processing Systems, pp. 802\u2013810. MIT Press (2015)"},{"key":"27_CR34","unstructured":"Jaderberg, M., et al.: Reinforcement Learning with Unsupervised Auxiliary Tasks. https:\/\/arxiv.org\/abs\/1611.05397. Accessed 16 Nov 2016"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-04182-3_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:21:05Z","timestamp":1709824865000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-04182-3_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030041816","9783030041823"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04182-3_27","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"18 November 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Siem Reap","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cambodia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/iconip\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"575","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"401","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"6","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}