{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T16:50:58Z","timestamp":1742921458456,"version":"3.40.3"},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030638320"},{"type":"electronic","value":"9783030638337"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-63833-7_24","type":"book-chapter","created":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T06:03:35Z","timestamp":1605765815000},"page":"283-294","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Reinforcement Learning with Temporal-Awareness Network"],"prefix":"10.1007","author":[{"given":"Ze-yu","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian-wei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weimin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"key":"24_CR1","unstructured":"Bunel, R., Hausknecht, M., Devlin, J., Singh, R., Kohli, P.: Leveraging grammar and reinforcement learning for neural program synthesis. arXiv preprint arXiv:1805.04276 (2018)"},{"key":"24_CR2","doi-asserted-by":"crossref","unstructured":"Zhang, T., Kahn, G., Levine, S., Abbeel, P.: Learning deep control policies for autonomous aerial vehicles with MPC-guided policy search. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 528\u2013535. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487175"},{"key":"24_CR3","unstructured":"Kiran, B.R., et al.: Deep Reinforcement Learning for Autonomous Driving: A Survey. arXiv preprint arXiv:2002.00444 (2020)"},{"key":"24_CR4","unstructured":"Lipovetzky, N., Ramirez, M., Geffner, H.: Classical planning with simulators: results on the Atari video games. In 24th International Joint Conference on Artificial Intelligence (2015)"},{"key":"24_CR5","unstructured":"Aldape, P., Sowell, S.: Reinforcement Learning for a Simple Racing Game (2018)"},{"key":"24_CR6","first-page":"1106","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25, 1106\u20131114 (2012)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"24_CR7","doi-asserted-by":"crossref","unstructured":"Sermanet, P., Kavukcuoglu, K., Chintala, S., LeCun, Y.: Pedestrian detection with unsupervised multi-stage feature learning. In: Proceedings of the International Conference on Computer Vision and Pattern Recognition (2013)","DOI":"10.1109\/CVPR.2013.465"},{"key":"24_CR8","unstructured":"Mnih, V.: Machine Learning for Aerial Image Labeling. Ph.D. thesis, University of Toronto (2013)"},{"key":"24_CR9","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"24_CR10","unstructured":"Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.: Action conditional video prediction using deep networks in Atari games. In: Advances in Neural Information Processing Systems, vol. 2863\u20132871 (2015)"},{"key":"24_CR11","unstructured":"Watter, M., Springenberg, J., Boedecker, J., Riedmiller, M.: Embed to control: a locally linear latent dynamics model for control from raw images. In: Advances in Neural Information Processing Systems, pp. 2746\u20132754 (2015)"},{"issue":"28","key":"24_CR12","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1016\/j.ifacol.2015.12.271","volume":"48","author":"N Wahlstr\u00f6m","year":"2015","unstructured":"Wahlstr\u00f6m, N., Sch\u00f6n, T.B., Deisenroth, M.P.: Learning deep dynamical models from image pixels. IFAC-PapersOnLine 48(28), 1059\u20131064 (2015)","journal-title":"IFAC-PapersOnLine"},{"issue":"7540","key":"24_CR13","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":"3\u20134","key":"24_CR14","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/BF00992699","volume":"8","author":"L-J Lin","year":"1992","unstructured":"Lin, L.-J.: Self-improving reactive agents based on reinforcement learning, planning and teaching. Mach. Learn. 8(3\u20134), 293\u2013321 (1992). https:\/\/doi.org\/10.1007\/BF00992699","journal-title":"Mach. Learn."},{"key":"24_CR15","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897 (2015)"},{"key":"24_CR16","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"24_CR17","unstructured":"Mnih, V., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"key":"24_CR18","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent Q-learning for partially observable MDPs. In AAAI Fall Symposium Series (2015)"},{"issue":"1","key":"24_CR19","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"24_CR20","unstructured":"Vu, T., Tran, L.: FlapAI Bird: Training an Agent to Play Flappy Bird Using Reinforcement Learning Techniques. arXiv preprint arXiv:2003.09579 (2020)"},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Piper, M., Bhounsule, P., Castillo-Villar, K.K.: How to beat flappy bird: a mixed-integer model predictive control approach. In: ASME Dynamic Systems and Control Conference. American Society of Mechanical Engineers Digital Collection (2017)","DOI":"10.1115\/DSCC2017-5285"},{"key":"24_CR22","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"24_CR23","unstructured":"Bellemare, M., Veness, J., Bowling, M.: Bayesian learning of recursively factored environments. In: Proceedings of the 13th International Conference on Machine Learning, pp. 1211\u20131219 (2013)"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63833-7_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T10:59:48Z","timestamp":1710327588000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63833-7_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030638320","9783030638337"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63833-7_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"20 November 2020","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":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 November 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 November 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.apnns.org\/ICONIP2020","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"618","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":"187","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":"189","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":"30% - 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":"3.18","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":"3.68","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Due to COVID-19 pandemic the conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}