{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:52:24Z","timestamp":1742950344709,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":21,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811623356"},{"type":"electronic","value":"9789811623363"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-981-16-2336-3_29","type":"book-chapter","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T16:17:17Z","timestamp":1620145037000},"page":"317-324","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Selective Transition Collection in Experience Replay"],"prefix":"10.1007","author":[{"given":"Feng","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuling","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjia","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,5]]},"reference":[{"key":"29_CR1","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"29_CR2","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., et al.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"29_CR3","unstructured":"Mnih, V., Badia, A.P., Mirza, M., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"29_CR4","unstructured":"Heess, N., Dhruva, T.B., Sriram, S., et al.: Emergence of locomotion behaviours in rich environments. arXiv preprint arXiv:1707.02286 (2017)"},{"key":"29_CR5","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"issue":"6","key":"29_CR6","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1109\/MSP.2017.2743240","volume":"34","author":"K Arulkumaran","year":"2017","unstructured":"Arulkumaran, K., Deisenroth, M.P., Brundage, M., et al.: Deep reinforcement learning: a brief survey. IEEE Signal Process. Mag. 34(6), 26\u201338 (2017)","journal-title":"IEEE Signal Process. Mag."},{"key":"29_CR7","unstructured":"Schaul, T., et al.: Prioritized experience replay. arXiv preprint arXiv:1511.05952 (2015)"},{"issue":"3","key":"29_CR8","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1145\/203330.203343","volume":"38","author":"G Tesauro","year":"1995","unstructured":"Tesauro, G.: Temporal difference learning and TD-Gammon. Commun. ACM 38(3), 58\u201368 (1995)","journal-title":"Commun. ACM"},{"issue":"3","key":"29_CR9","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/S0019-9958(58)80003-0","volume":"1","author":"R Bellman","year":"1958","unstructured":"Bellman, R.: Dynamic programming and stochastic control processes. Inf. Control 1(3), 228\u2013239 (1958)","journal-title":"Inf. Control"},{"issue":"3\u20134","key":"29_CR10","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"29_CR11","unstructured":"Shelton, C.R.: Importance sampling for reinforcement learning with multiple objectives. Dissertation, Massachusetts Institute of Technology (2001)"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Hachiya, H, et al.: Adaptive importance sampling for value function approximation in off-policy reinforcement learning. Neural Netw. 22(10), 1399\u20131410 (2009)","DOI":"10.1016\/j.neunet.2009.01.002"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Uchibe, E., Doya, K.: Competitive-cooperative-concurrent reinforcement learning with importance sampling. In: Proceedings of International Conference on Simulation of Adaptive Behavior: From Animals and Animats (2004)","DOI":"10.7551\/mitpress\/3122.003.0037"},{"key":"29_CR14","unstructured":"Lopez-Paz, D., Ranzato, M.A.: Gradient episodic memory for continual learning. In: Advances in Neural Information Processing Systems (2017)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Lin, Z., et al.: Episodic memory deep Q-networks. arXiv preprint arXiv:1805.07603 (2018)","DOI":"10.24963\/ijcai.2018\/337"},{"key":"29_CR16","unstructured":"Fortunato, M., et al.: Generalization of reinforcement learners with working and episodic memory. In: Advances in Neural Information Processing Systems (2019)"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Isele, D., Cosgun, A.: Selective experience replay for lifelong learning. In: AAAI Conference on Artificial Intelligence 2018. Association for the Advancement of Artificial Intelligence (AAAI) (2018)","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"29_CR18","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"29_CR19","unstructured":"Zamora, I., et al.: Extending the OpenAI gym for robotics: a toolkit for reinforcement learning using ROS and Gazebo. arXiv preprint arXiv:1608.05742\u00a0(2016)"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"V\u00e1zquez-Canteli, J.R., et al.: Citylearn v1. 0: an OpenAI gym environment for demand response with deep reinforcement learning. In: Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (2019)","DOI":"10.1145\/3360322.3360998"},{"key":"29_CR21","unstructured":"Lillicrap, T.P., Hunt, J.J., Pritzel, A., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"}],"container-title":["Communications in Computer and Information Science","Cognitive Systems and Signal Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-16-2336-3_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,3]],"date-time":"2023-11-03T07:29:24Z","timestamp":1698996564000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-16-2336-3_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9789811623356","9789811623363"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-981-16-2336-3_29","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"5 May 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Cognitive Systems and Signal Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhuhai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"25 December 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 December 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsip2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iccsip2020.caai.cn\/","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":"120","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":"59","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":"49% - 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":"2","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","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)"}}]}}