{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T10:29:27Z","timestamp":1782296967704,"version":"3.54.5"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030893699","type":"print"},{"value":"9783030893705","type":"electronic"}],"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\/978-3-030-89370-5_5","type":"book-chapter","created":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T01:02:59Z","timestamp":1635728579000},"page":"60-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Adaptive Warm-Start MCTS in\u00a0AlphaZero-Like Deep Reinforcement\u00a0Learning"],"prefix":"10.1007","author":[{"given":"Hui","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike","family":"Preuss","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aske","family":"Plaat","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,11,1]]},"reference":[{"issue":"1","key":"5_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"CB Browne","year":"2012","unstructured":"Browne, C.B., et al.: A survey of Monte Carlo tree search methods. IEEE Trans. Comput. Intell. AI Games 4(1), 1\u201343 (2012)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"5_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1007\/978-3-540-87608-3_11","volume-title":"Computers and Games","author":"R Coulom","year":"2008","unstructured":"Coulom, R.: Whole-history rating: a Bayesian rating system for players of time-varying strength. In: van den Herik, H.J., Xu, X., Ma, Z., Winands, M.H.M. (eds.) CG 2008. LNCS, vol. 5131, pp. 113\u2013124. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-87608-3_11"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Gelly, S., Silver, D.: Combining online and offline knowledge in UCT. In: Proceedings of the 24th International Conference on Machine Learning, pp. 273\u2013280 (2007)","DOI":"10.1145\/1273496.1273531"},{"issue":"11","key":"5_CR4","doi-asserted-by":"publisher","first-page":"1856","DOI":"10.1016\/j.artint.2011.03.007","volume":"175","author":"S Gelly","year":"2011","unstructured":"Gelly, S., Silver, D.: Monte-Carlo tree search and rapid action value estimation in computer go. Artif. Intell. 175(11), 1856\u20131875 (2011)","journal-title":"Artif. Intell."},{"key":"5_CR5","unstructured":"Nair, S.: Alphazero general (2018). https:\/\/github.com\/suragnair\/alpha-zero-general. Accessed May 2018"},{"key":"5_CR6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59238-7","volume-title":"Learning to Play: Reinforcement Learning and Games","author":"A Plaat","year":"2020","unstructured":"Plaat, A.: Learning to Play: Reinforcement Learning and Games. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59238-7"},{"key":"5_CR7","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","volume":"61","author":"J Schmidhuber","year":"2015","unstructured":"Schmidhuber, J.: Deep learning in neural networks: an overview. Neural Netw. 61, 85\u2013117 (2015)","journal-title":"Neural Netw."},{"issue":"7698","key":"5_CR8","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/nature25978","volume":"555","author":"MH Segler","year":"2018","unstructured":"Segler, M.H., Preuss, M., Waller, M.P.: Planning chemical syntheses with deep neural networks and symbolic AI. Nature 555(7698), 604\u2013610 (2018)","journal-title":"Nature"},{"issue":"7587","key":"5_CR9","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(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"issue":"6419","key":"5_CR10","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D.: 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_CR11","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\u2013359 (2017)","journal-title":"Nature"},{"key":"5_CR12","volume-title":"Reinforcement learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement learning: An Introduction. MIT Press, Cambridge (2018)"},{"issue":"3","key":"5_CR13","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":"7782","key":"5_CR14","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O.: Grandmaster level in starcraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"5_CR15","series-title":"Communications in Computer and Information Science","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1007\/978-3-030-31978-6_11","volume-title":"Artificial Intelligence","author":"H Wang","year":"2019","unstructured":"Wang, H., Emmerich, M., Plaat, A.: Assessing the potential of classical Q-learning in general game playing. In: Atzmueller, M., Duivesteijn, W. (eds.) BNAIC 2018. CCIS, vol. 1021, pp. 138\u2013150. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-31978-6_11"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Wang, H., Emmerich, M., Preuss, M., Plaat, A.: Alternative loss functions in alphazero-like self-play. In: 2019 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 155\u2013162. IEEE (2019)","DOI":"10.1109\/SSCI44817.2019.9002814"},{"key":"5_CR17","unstructured":"Wang, H., Emmerich, M., Preuss, M., Plaat, A.: Analysis of hyper-parameters for small games: Iterations or epochs in self-play? arXiv preprint arXiv:2003.05988 (2020)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Wang, H., Preuss, M., Emmerich, M., Plaat, A.: Tackling morpion solitaire with alphazero-like ranked reward reinforcement learning. arXiv preprint arXiv:2006.07970 (2020)","DOI":"10.1109\/SYNASC51798.2020.00033"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Wang, H., Preuss, M., Plaat, A.: Warm-start alphazero self-play search enhancements. In: Proceedings of the Parallel Problem Solving from Nature - PPSN XVI, pp. 528\u2013542 (2020)","DOI":"10.1007\/978-3-030-58115-2_37"},{"key":"5_CR20","unstructured":"Wu, D.J.: Accelerating self-play learning in go. arXiv preprint arXiv:1902.10565 (2019)"}],"container-title":["Lecture Notes in Computer Science","PRICAI 2021: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-89370-5_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T01:12:14Z","timestamp":1635729134000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-89370-5_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030893699","9783030893705"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-89370-5_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"1 November 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 November 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2021","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"382","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":"93","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":"28","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":"24% - 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":"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)"}}]}}