{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T02:05:51Z","timestamp":1743127551841,"version":"3.40.3"},"publisher-location":"Cham","reference-count":15,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030041786"},{"type":"electronic","value":"9783030041793"}],"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\/978-3-030-04179-3_57","type":"book-chapter","created":{"date-parts":[[2018,11,17]],"date-time":"2018-11-17T07:12:42Z","timestamp":1542438762000},"page":"645-654","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep Deterministic Policy Gradient with Clustered Prioritized Sampling"],"prefix":"10.1007","author":[{"given":"Wen","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"YuChen","family":"Fu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,11,18]]},"reference":[{"key":"57_CR1","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Playing Atari with deep reinforcement learning. In: Proceedings of Workshops at the 26th Neural Information Processing Systems, Lake Tahoe, USA (2013)"},{"issue":"7540","key":"57_CR2","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.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"7587","key":"57_CR3","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"57_CR4","unstructured":"Schulman, J., Moritz, P., Levine, S., et al.: High-dimensional continuous control using generalized advantage estimation. In: Proceedings of the International Conference on Learning Representations (2015)"},{"key":"57_CR5","unstructured":"Watter, M., Springenberg, J.T., Riedmiller, M., et al.: Embed to control: a locally linear latent dynamics model for control from raw images. In: Advances in Neural Information Processing System, pp. 2728\u20132736 (2015)"},{"key":"57_CR6","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., et al.: Continuous control with deep reinforcement learning. In: Proceedings of the International Conference on Learning Representations (2016)"},{"key":"57_CR7","unstructured":"Silver, D., Lever, G., Heess, N., et al.: Deterministic policy gradient algorithms. In: Proceedings of the International Conference on Machine Learning, pp. 387\u2013395 (2014)"},{"key":"57_CR8","unstructured":"Heess, N., Wayne, G., Silver, D., et al.: Learning continuous control policies by stochastic value gradients. In: Advances in Neural Information Processing System, pp. 2926\u20132934 (2015)"},{"key":"57_CR9","unstructured":"Levine, S., Levine, S., Levine, S., et al.: Continuous deep Q-learning with model-based acceleration. In: Proceedings of the 33th International Conference on Machine Learning, pp. 2829\u20132838 (2016)"},{"key":"57_CR10","unstructured":"Levine, S., Abbeel, P.: Learning neural network policies with guided policy search under unknown dynamics. In: Advances in Neural Information Processing Systems, pp. 1071\u20131079 (2014)"},{"issue":"5","key":"57_CR11","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.tins.2010.01.006","volume":"33","author":"J O\u2019Neill","year":"2010","unstructured":"O\u2019Neill, J., Pleydell-Bouverie, B., Dupret, D., et al.: Play it again: reactivation of waking experience and memory. Trends Neurosci. 33(5), 220\u2013229 (2010)","journal-title":"Trends Neurosci."},{"issue":"5","key":"57_CR12","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.neunet.2012.11.007","volume":"41","author":"P Wawrzy\u0144ski","year":"2013","unstructured":"Wawrzy\u0144ski, P., Tanwani, A.K.: Autonomous reinforcement learning with experience replay. Neural Netw. 41(5), 156 (2013)","journal-title":"Neural Netw."},{"issue":"2","key":"57_CR13","doi-asserted-by":"publisher","first-page":"407","DOI":"10.3934\/ipi.2011.5.407","volume":"5","author":"SH Kang","year":"2017","unstructured":"Kang, S.H., Sandberg, B., Yip, A.M.: A regularized k-means and multiphase scale segmentation. Inverse Probl. Imaging 5(2), 407\u2013429 (2017)","journal-title":"Inverse Probl. Imaging"},{"issue":"2\u20133","key":"57_CR14","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1023\/A:1013689704352","volume":"47","author":"P Auer","year":"2002","unstructured":"Auer, P., Cesa-Bianchi, N., Fischer, P.: Finite-time analysis of the multiarmed bandit problem. Mach. Learn. 47(2\u20133), 235\u2013256 (2002)","journal-title":"Mach. Learn."},{"key":"57_CR15","unstructured":"Mnih, V., Badia, A.P., Mirza, M., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings of the International Conference on Machine Learning, New York, USA, pp. 1928\u20131937 (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\/978-3-030-04179-3_57","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T15:32:32Z","timestamp":1709825552000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-04179-3_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030041786","9783030041793"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-04179-3_57","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)"}}]}}