{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T05:51:57Z","timestamp":1773294717676,"version":"3.50.1"},"publisher-location":"Cham","reference-count":18,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030461324","type":"print"},{"value":"9783030461331","type":"electronic"}],"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"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-46133-1_5","type":"book-chapter","created":{"date-parts":[[2020,4,30]],"date-time":"2020-04-30T07:08:58Z","timestamp":1588230538000},"page":"69-85","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Practical Open-Loop Optimistic Planning"],"prefix":"10.1007","author":[{"given":"Edouard","family":"Leurent","sequence":"first","affiliation":[]},{"given":"Odalric-Ambrym","family":"Maillard","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,4,30]]},"reference":[{"key":"5_CR1","volume-title":"Dynamic Programming","author":"R Bellman","year":"1957","unstructured":"Bellman, R.: Dynamic Programming. Princeton University Press, Princeton (1957)"},{"key":"5_CR2","unstructured":"Bubeck, S., Munos, R.: Open loop optimistic planning. In: Proceedings of COLT (2010)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Bu\u015foniu, L., Daniels, A., Munos, R., Babuska, R.: Optimistic planning for continuous-action deterministic systems. In: IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, ADPRL (2013)","DOI":"10.1109\/ADPRL.2013.6614991"},{"key":"5_CR4","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.automatica.2018.03.009","volume":"92","author":"L Bu\u015foniu","year":"2018","unstructured":"Bu\u015foniu, L., P\u00e1ll, E., Munos, R.: Continuous-action planning for discounted infinite-horizon nonlinear optimal control with Lipschitz values. Automatica 92, 100\u2013108 (2018)","journal-title":"Automatica"},{"issue":"3","key":"5_CR5","doi-asserted-by":"publisher","first-page":"1516","DOI":"10.1214\/13-AOS1119","volume":"41","author":"O Capp\u00e9","year":"2013","unstructured":"Capp\u00e9, O., Garivier, A., Maillard, O.A., Munos, R., Stoltz, G.: Kullback-Leibler upper confidence bounds for optimal sequential allocation. Ann. Stat. 41(3), 1516\u20131541 (2013)","journal-title":"Ann. Stat."},{"key":"5_CR6","unstructured":"Chevalier-Boisvert, M., Willems, L., Pal, S.: Minimalistic gridworld environment for openai gym (2018). https:\/\/github.com\/maximecb\/gym-minigrid"},{"key":"5_CR7","unstructured":"Coquelin, P.A., Munos, R.: Bandit algorithms for tree search. In: Proceedings of UAI (2007)"},{"key":"5_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1007\/978-3-540-75538-8_7","volume-title":"Computers and Games","author":"R Coulom","year":"2007","unstructured":"Coulom, R.: Efficient selectivity and backup operators in Monte-Carlo tree search. In: van den Herik, H.J., Ciancarini, P., Donkers, H.H.L.M.J. (eds.) CG 2006. LNCS, vol. 4630, pp. 72\u201383. Springer, Heidelberg (2007). https:\/\/doi.org\/10.1007\/978-3-540-75538-8_7"},{"key":"5_CR9","unstructured":"Grill, J.B., Valko, M., Munos, R.: Blazing the trails before beating the path: sample-efficient Monte-Carlo planning. In: Proceedings of NeurIPS (2016)"},{"key":"5_CR10","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-3-540-89722-4_12","volume-title":"Recent Advances in Reinforcement Learning","author":"J-F Hren","year":"2008","unstructured":"Hren, J.-F., Munos, R.: Optimistic planning of deterministic systems. In: Girgin, S., Loth, M., Munos, R., Preux, P., Ryabko, D. (eds.) EWRL 2008. LNCS (LNAI), vol. 5323, pp. 151\u2013164. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-89722-4_12"},{"key":"5_CR11","unstructured":"Kearns, M., Mansour, Y., Ng, A.Y.: A sparse sampling algorithm for near-optimal planning in large Markov decision processes. In: Proceedings of IJCAI (2002)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based Monte-Carlo planning. In: Proceedings of ECML (2006)","DOI":"10.1007\/11871842_29"},{"key":"5_CR13","unstructured":"Leurent, E.: An environment for autonomous driving decision-making (2018). https:\/\/github.com\/eleurent\/highway-env"},{"key":"5_CR14","doi-asserted-by":"crossref","unstructured":"Munos, R.: From Bandits to Monte-Carlo tree search: the optimistic principle applied to optimization. Found. Trends\u00ae Mach. Learn. 7, 1\u2013129 (2014)","DOI":"10.1561\/2200000038"},{"key":"5_CR15","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484\u2013503 (2016)","journal-title":"Nature"},{"issue":"6419","key":"5_CR16","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"issue":"7676","key":"5_CR17","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354 (2017)","journal-title":"Nature"},{"key":"5_CR18","unstructured":"Szorenyi, B., Kedenburg, G., Munos, R.: Optimistic planning in Markov decision processes using a generative model. In: Proceedings of NeurIPS (2014)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-46133-1_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T22:05:36Z","timestamp":1745964336000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-46133-1_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030461324","9783030461331"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-46133-1_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"30 April 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"W\u00fcrzburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/ecmlpkdd2019.org\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"733","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":"130","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":"18% - 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":"3.04","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":"5.3","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"ECML PKDD Workshops Information: single-blind review, submissions: 200, full papers accepted: 70, short papers accepted: 46","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)"}}]}}