{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T00:38:55Z","timestamp":1726101535034},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030616151"},{"type":"electronic","value":"9783030616168"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/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":"http:\/\/www.springer.com\/tdm"},{"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\/978-3-030-61616-8_25","type":"book-chapter","created":{"date-parts":[[2020,10,16]],"date-time":"2020-10-16T23:07:42Z","timestamp":1602889662000},"page":"308-320","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Understanding Failures of Deterministic Actor-Critic with Continuous Action Spaces and Sparse Rewards"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-6530-8784","authenticated-orcid":false,"given":"Guillaume","family":"Matheron","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2358-2915","authenticated-orcid":false,"given":"Nicolas","family":"Perrin","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0002-8544-0229","authenticated-orcid":false,"given":"Olivier","family":"Sigaud","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,10,14]]},"reference":[{"key":"25_CR1","unstructured":"Achiam, J., Knight, E., Abbeel, P.: Towards characterizing divergence in deep q-learning. arXiv:1903.08894 (2019)"},{"key":"25_CR2","unstructured":"Ahmed, Z., Roux, N.L., Norouzi, M., Schuurmans, D.: Understanding the impact of entropy on policy optimization. arXiv:1811.11214 (2019)"},{"key":"25_CR3","unstructured":"Baird, L.C., Klopf, A.H.: Technical Report WL-TR-93-1147. Wright-Patterson AIr Force Base, Ohio, Wright Laboratory (1993)"},{"key":"25_CR4","unstructured":"Boyan, J.A., Moore, A.W.: Generalization in reinforcement learning: safely approximating the value function. In: Advances in Neural Information Processing Systems, pp. 369\u2013376 (1995)"},{"key":"25_CR5","unstructured":"Colas, C., Sigaud, O., Oudeyer, P.Y.: GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms. arXiv:1802.05054 (2018)"},{"key":"25_CR6","unstructured":"Fortunato, M., et al.: Noisy Networks for Exploration. arXiv:1706.10295 (2017)"},{"key":"25_CR7","unstructured":"Fujimoto, S., van Hoof, H., Meger, D.: Addressing Function Approximation Error in Actor-Critic Methods. ICML (2018)"},{"key":"25_CR8","unstructured":"Fujimoto, S., Meger, D., Precup, D.: Off-Policy Deep Reinforcement Learning without Exploration. arXiv:1812.02900 (2018)"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Geist, M., Pietquin, O.: Parametric value function approximation: a unified view. In: ADPRL 2011, Paris, France, pp. 9\u201316 (2011)","DOI":"10.1109\/ADPRL.2011.5967355"},{"key":"25_CR10","unstructured":"van Hasselt, H., Doron, Y., Strub, F., Hessel, M., Sonnerat, N., Modayil, J.: Deep Reinforcement Learning and the Deadly Triad. arXiv:1812.02648 (2018)"},{"key":"25_CR11","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv:1509.02971 (2015)"},{"key":"25_CR12","unstructured":"Mnih, V., et al.: Playing Atari with Deep Reinforcement Learning. arXiv:1312.5602 (2013)"},{"issue":"7540","key":"25_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"},{"key":"25_CR14","unstructured":"Plappert, M., et al.: Parameter space noise for exploration. arXiv preprint arXiv:1706.01905 (2017)"},{"key":"25_CR15","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395 (2014)"},{"key":"25_CR16","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"25_CR17","unstructured":"Tsitsiklis, J.N., Van Roy, B.: Analysis of temporal-difference learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1075\u20131081 (1997)"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-61616-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T10:17:26Z","timestamp":1619259446000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-61616-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030616151","9783030616168"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-61616-8_25","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":"14 October 2020","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":"Bratislava","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Slovakia","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":"15 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2020\/","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":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"249","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":"139","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":"56% - 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":"2.5","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)"}},{"value":"*The conference was postponed to 2021 due to the COVID-19 pandemic.","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)"}}]}}