{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T19:51:26Z","timestamp":1743105086196,"version":"3.40.3"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031216886"},{"type":"electronic","value":"9783031216893"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-21689-3_8","type":"book-chapter","created":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T10:03:56Z","timestamp":1668765836000},"page":"96-110","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["When Less May Be More: Exploring Similarity to\u00a0Improve Experience Replay"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2874-2930","authenticated-orcid":false,"given":"Daniel Eug\u00eanio","family":"Neves","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8565-8386","authenticated-orcid":false,"given":"Lucila","family":"Ishitani","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0804-1790","authenticated-orcid":false,"given":"Zenilton Kleber Gon\u00e7alves","family":"do Patroc\u00ednio J\u00fanior","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,19]]},"reference":[{"key":"8_CR1","unstructured":"Bellemare, M.G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: Precup, D., Teh, Y.W. (eds.) Proceedings of the 34th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 70, pp. 449\u2013458 (2017)"},{"key":"8_CR2","unstructured":"Fedus, W., et al.: Revisiting fundamentals of experience replay. In: Daum\u00e9, H., Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 119, pp. 3061\u20133071 (2020)"},{"key":"8_CR3","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. In: Proceedings of the International Conference on Representation Learning (2018)"},{"key":"8_CR4","unstructured":"van Hasselt, H.: Double Q-learning. In: Lafferty, J.D., Williams, C.K.I., Shawe-Taylor, J., Zemel, R.S., Culotta, A. (eds.) Advances in Neural Information Processing Systems 23 (NIPS), pp. 2613\u20132621 (2010)"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"8_CR6","unstructured":"Hausknecht, M., Stone, P.: Deep recurrent q-learning for partially observable mdps. In: AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (2015)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Hessel, M., et al.: Rainbow: Combining improvements in deep reinforcement learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.11796"},{"issue":"3\u20134","key":"8_CR8","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1007\/BF00992699","volume":"8","author":"LJ 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)","journal-title":"Mach. Learn."},{"key":"8_CR9","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1613\/jair.5699","volume":"61","author":"MC Machado","year":"2018","unstructured":"Machado, M.C., Bellemare, M.G., Talvitie, E., Veness, J., Hausknecht, M.J., Bowling, M.: Revisiting the arcade learning environment: Evaluation protocols and open problems for general agents. J. Artifi. Intell. Res. 61, 523\u2013562 (2018)","journal-title":"J. Artifi. Intell. Res."},{"key":"8_CR10","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of The 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 48, pp. 1928\u20131937 (2016)"},{"issue":"7540","key":"8_CR11","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"},{"key":"8_CR12","unstructured":"Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. In: Proceedings of the International Conference on Representation Learning (2016)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Sutton, R.S.: Reinforcement learning architectures. In: Proceedings ISKIT 1992 International Symposium on Neural Information Processing (1992)","DOI":"10.1007\/978-1-4615-3618-5"},{"key":"8_CR14","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: Balcan, M.F., Weinberger, K.Q. (eds.) Proceedings of The 33rd International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 48, pp. 1995\u20132003 (2016)"},{"issue":"3","key":"8_CR15","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1007\/BF00992698","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"8_CR16","unstructured":"Wei, Q., Ma, H., Chen, C., Dong, D.: Deep reinforcement learning with quantum-inspired experience replay. IEEE Trans. Cybern. 1\u201313 (2021)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Zha, D., Lai, K.H., Zhou, K., Hu, X.: Experience replay optimization. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI), pp. 4243\u20134249 (2019)","DOI":"10.24963\/ijcai.2019\/589"},{"key":"8_CR18","unstructured":"Zhang, S., Sutton, R.S.: A deeper look at experience replay. In: Deep Reinforcement Learning Symposium (NIPS) (2017)"}],"container-title":["Lecture Notes in Computer Science","Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-21689-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T00:12:22Z","timestamp":1668989542000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-21689-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031216886","9783031216893"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-21689-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"19 November 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BRACIS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazilian Conference on Intelligent Systems","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Campinas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Brazil","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 November 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bracis2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www2.sbc.org.br\/bracis2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"JEMS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"225","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":"89","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":"40% - 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","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":"4","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)"}}]}}