{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T00:49:02Z","timestamp":1743122942796,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031441974"},{"type":"electronic","value":"9783031441981"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-44198-1_16","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:02:34Z","timestamp":1695283354000},"page":"184-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Efficient Reinforcement Learning Using State-Action Uncertainty with\u00a0Multiple Heads"],"prefix":"10.1007","author":[{"given":"Tomoharu","family":"Aizu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takeru","family":"Oba","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Norimichi","family":"Ukita","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"key":"16_CR1","unstructured":"Badia, A.P., et al.: Agent57: outperforming the Atari human benchmark. In: ICML, pp. 507\u2013517 (2020)"},{"key":"16_CR2","unstructured":"Badia, A.P., et al.: Never give up: learning directed exploration strategies. In: ICLR (2020)"},{"key":"16_CR3","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents (extended abstract). In: IJCAI, pp. 4148\u20134152 (2015)"},{"key":"16_CR4","unstructured":"Bellemare, M.G., Srinivasan, S., Ostrovski, G., Schaul, T., Saxton, D., Munos, R.: Unifying count-based exploration and intrinsic motivation. In: NIPS, pp. 1471\u20131479 (2016)"},{"key":"16_CR5","unstructured":"Burda, Y., Edwards, H., Storkey, A.J., Klimov, O.: Exploration by random network distillation. In: ICLR (2019)"},{"key":"16_CR6","unstructured":"Chen, R.Y., Sidor, S., Abbeel, P., Schulman, J.: UCB and InfoGain exploration via Q-ensembles. CoRR abs\/1706.01502 (2017)"},{"key":"16_CR7","unstructured":"Dabney, W., Ostrovski, G., Barreto, A.: Temporally-extended $$\\epsilon $$-greedy exploration. In: ICLR (2021)"},{"key":"16_CR8","unstructured":"Gimelfarb, M., Sanner, S., Lee, C.: Epsilon-BMC: a Bayesian ensemble approach to epsilon-greedy exploration in model-free reinforcement learning. In: UAI, pp. 476\u2013485 (2019)"},{"key":"16_CR9","unstructured":"Osband, I., Blundell, C., Pritzel, A., Roy, B.V.: Deep exploration via bootstrapped DQN. In: NIPS, pp. 4026\u20134034 (2016)"},{"key":"16_CR10","unstructured":"Pislar, M., Szepesvari, D., Ostrovski, G., Borsa, D.L., Schaul, T.: When should agents explore? In: ICLR (2022)"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"da Silva, F.L., Hernandez-Leal, P., Kartal, B., Taylor, M.E.: Uncertainty-aware action advising for deep reinforcement learning agents. In: EAAI, pp. 5792\u20135799 (2020)","DOI":"10.1609\/aaai.v34i04.6036"},{"issue":"8","key":"16_CR12","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.1016\/j.jcss.2007.08.009","volume":"74","author":"AL Strehl","year":"2008","unstructured":"Strehl, A.L., Littman, M.L.: An analysis of model-based interval estimation for Markov decision processes. J. Comput. Syst. Sci. 74(8), 1309\u20131331 (2008)","journal-title":"J. Comput. Syst. Sci."},{"key":"16_CR13","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. The MIT Press, London (2018)","edition":"2"},{"key":"16_CR14","unstructured":"Tang, H., et al.: #Exploration: a study of count-based exploration for deep reinforcement learning. In: NIPS, pp. 2753\u20132762 (2017)"},{"key":"16_CR15","unstructured":"Tarbouriech, J., Pirotta, M., Valko, M., Lazaric, A.: A provably efficient sample collection strategy for reinforcement learning. In: NeurIPS, pp. 7611\u20137624 (2021)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Tokic, M.: Adaptive $$\\epsilon $$-greedy exploration in reinforcement learning based on value difference. In: KI, vol. 6359, pp. 203\u2013210 (2010)","DOI":"10.1007\/978-3-642-16111-7_23"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44198-1_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T22:11:58Z","timestamp":1701209518000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44198-1_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031441974","9783031441981"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44198-1_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","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":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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":"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)"}},{"value":"type of other papers accepted  : 9 Abstract","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)"}}]}}