{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:44:55Z","timestamp":1766137495943,"version":"3.40.3"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030581145"},{"type":"electronic","value":"9783030581152"}],"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"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-58115-2_37","type":"book-chapter","created":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T22:02:51Z","timestamp":1598997771000},"page":"528-542","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Warm-Start AlphaZero Self-play Search Enhancements"],"prefix":"10.1007","author":[{"given":"Hui","family":"Wang","sequence":"first","affiliation":[]},{"given":"Mike","family":"Preuss","sequence":"additional","affiliation":[]},{"given":"Aske","family":"Plaat","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,2]]},"reference":[{"issue":"7587","key":"37_CR1","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 (2016)","journal-title":"Nature"},{"issue":"7676","key":"37_CR2","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"},{"issue":"6419","key":"37_CR3","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":"2","key":"37_CR4","first-page":"114","volume":"2","author":"J Tao","year":"2016","unstructured":"Tao, J., Lin, W., Xiaofeng, H.: Principle analysis on AlphaGo and perspective in military application of artificial intelligence. J. Command Control 2(2), 114\u2013120 (2016)","journal-title":"J. Command Control"},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Zhang, Z.: When doctors meet with AlphaGo: potential application of machine learning to clinical medicine. Ann. Transl. Med. 4(6) (2016)","DOI":"10.21037\/atm.2016.03.25"},{"issue":"1","key":"37_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"C Browne","year":"2012","unstructured":"Browne, C., 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"},{"issue":"7540","key":"37_CR7","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":"37_CR8","doi-asserted-by":"crossref","unstructured":"Plaat, A.: Learning to play\u2013reinforcement learning and games (2020)","DOI":"10.1007\/978-3-030-59238-7"},{"key":"37_CR9","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"},{"key":"37_CR10","unstructured":"Nair, S.: AlphaZero general. https:\/\/github.com\/suragnair\/alpha-zero-general (2018). Accessed May 2018"},{"key":"37_CR11","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":"37_CR12","unstructured":"Ruijl, B., Vermaseren, J., Plaat, A., van den Herik, J.: Combining simulated annealing and Monte Carlo tree search for expression simplification. In: Proceedings of the 6th International Conference on Agents and Artificial Intelligence-Volume 1, pp. 724\u2013731. SCITEPRESS-Science and Technology Publications, Lda (2014)"},{"key":"37_CR13","unstructured":"Chaslot, G., Bakkes, S., Szita, I., Spronck, P.: Monte-Carlo tree search: a new framework for game AI. In: AIIDE (2008)"},{"issue":"11","key":"37_CR14","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":"37_CR15","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."},{"key":"37_CR16","unstructured":"Clark, C., Storkey, A.: Training deep convolutional neural networks to play go. In: International Conference on Machine Learning, pp. 1766\u20131774 (2015)"},{"issue":"3","key":"37_CR17","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"},{"key":"37_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/3-540-45579-5_18","volume-title":"Computers and Games","author":"EA Heinz","year":"2001","unstructured":"Heinz, E.A.: New self-play results in computer chess. In: Marsland, T., Frank, I. (eds.) CG 2000. LNCS, vol. 2063, pp. 262\u2013276. Springer, Heidelberg (2001). https:\/\/doi.org\/10.1007\/3-540-45579-5_18"},{"issue":"02","key":"37_CR19","first-page":"57","volume":"2","author":"MA Wiering","year":"2010","unstructured":"Wiering, M.A., et al.: Self-play and using an expert to learn to play backgammon with temporal difference learning. J. Intell. Learn. Syst. Appl. 2(02), 57 (2010)","journal-title":"J. Intell. Learn. Syst. Appl."},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Van Der Ree, M., Wiering, M.: Reinforcement learning in the game of Othello: learning against a fixed opponent and learning from self-play. In: IEEE Symposium on Adaptive Dynamic Programming And Reinforcement Learning (ADPRL), pp. 108\u2013115. IEEE (2013)","DOI":"10.1109\/ADPRL.2013.6614996"},{"issue":"6","key":"37_CR21","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1109\/TEVC.2005.856212","volume":"9","author":"TP Runarsson","year":"2005","unstructured":"Runarsson, T.P., Lucas, S.M.: Coevolution versus self-play temporal difference learning for acquiring position evaluation in small-board go. IEEE Trans. Evol. Comput. 9(6), 628\u2013640 (2005)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"37_CR22","unstructured":"Wang, H., Emmerich, M., Plaat, A.: Monte Carlo Q-learning for general game playing. arXiv preprint arXiv:1802.05944 (2018)"},{"key":"37_CR23","unstructured":"Wu, D.J.: Accelerating self-play learning in go. arXiv preprint arXiv:1902.10565 (2019)"},{"issue":"2","key":"37_CR24","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/0304-3975(94)90131-7","volume":"123","author":"S Iwata","year":"1994","unstructured":"Iwata, S., Kasai, T.: The Othello game on an n * n board is PSPACE-complete. Theor. Comput. Sci. 123(2), 329\u2013340 (1994)","journal-title":"Theor. Comput. Sci."},{"issue":"4","key":"37_CR25","doi-asserted-by":"publisher","first-page":"165","DOI":"10.3233\/ICG-1988-11410","volume":"11","author":"LV Allis","year":"1988","unstructured":"Allis, L.V.: A knowledge-based approach of connect-four. ICGA J. 11(4), 165 (1988)","journal-title":"ICGA J."},{"issue":"1","key":"37_CR26","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/BF00288536","volume":"13","author":"S Reisch","year":"1980","unstructured":"Reisch, S.: Gobang ist pspace-vollst\u00e4ndig. Acta Informatica 13(1), 59\u201366 (1980)","journal-title":"Acta Informatica"},{"issue":"3","key":"37_CR27","doi-asserted-by":"publisher","first-page":"189","DOI":"10.3233\/ICG-1997-20311","volume":"20","author":"M Buro","year":"1997","unstructured":"Buro, M.: The Othello match of the year: Takeshi Murakami vs. Logistello. ICGA J. 20(3), 189\u2013193 (1997)","journal-title":"ICGA J."},{"issue":"3","key":"37_CR28","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1109\/TEVC.2005.843750","volume":"9","author":"SY Chong","year":"2005","unstructured":"Chong, S.Y., Tan, M.K., White, J.D.: Observing the evolution of neural networks learning to play the game of Othello. IEEE Trans. Evol. Comput. 9(3), 240\u2013251 (2005)","journal-title":"IEEE Trans. Evol. Comput."},{"key":"37_CR29","doi-asserted-by":"crossref","unstructured":"Thill, M., Bagheri, S., Koch, P., Konen, W.: Temporal difference learning with eligibility traces for the game connect four. In: IEEE Conference on Computational Intelligence and Games, pp. 1\u20138. IEEE (2014)","DOI":"10.1109\/CIG.2014.6932870"},{"key":"37_CR30","first-page":"051","volume":"7","author":"ML Zhang","year":"2012","unstructured":"Zhang, M.L., Wu, J., Li, F.Z.: Design of evaluation-function for computer gobang game system. J. Comput. Appl. 7, 051 (2012)","journal-title":"J. Comput. Appl."},{"key":"37_CR31","unstructured":"Banerjee, B., Stone, P.: General game learning using knowledge transfer. In: IJCAI, pp. 672\u2013677 (2007)"},{"key":"37_CR32","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":"37_CR33","doi-asserted-by":"crossref","unstructured":"Wang, H., Emmerich, M., Preuss, M., Plaat, A.: Alternative loss functions in alphazero-like self-play. In: IEEE Symposium Series on Computational Intelligence (SSCI), pp. 155\u2013162. IEEE (2019)","DOI":"10.1109\/SSCI44817.2019.9002814"},{"key":"37_CR34","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)"},{"key":"37_CR35","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"1","key":"37_CR36","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"37_CR37","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s10472-011-9258-6","volume":"61","author":"CD Rosin","year":"2011","unstructured":"Rosin, C.D.: Multi-armed bandits with episode context. Ann. Mathe. Artif. Intell. 61(3), 203\u2013230 (2011). https:\/\/doi.org\/10.1007\/s10472-011-9258-6","journal-title":"Ann. Mathe. Artif. Intell."},{"key":"37_CR38","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1109\/TCIAIG.2017.2738156","volume":"10","author":"N Justesen","year":"2017","unstructured":"Justesen, N., Mahlmann, T., Risi, S., Togelius, J.: Playing multi-action adversarial games: online evolutionary planning versus tree search. IEEE Trans. Comput. Intell. AI Games 10, 281\u2013291 (2017)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"37_CR39","unstructured":"Perez, D., Samothrakis, S., Lucas, S., Rohlfshagen, P.: Rolling horizon evolution versus tree search for navigation in single-player real-time games. In: Proceedings of the 15th Annual Conference on Genetic and Evolutionary Computation, GECCO 2013, pp. 351\u2013358. New York (2013). Association for Computing Machinery"},{"key":"37_CR40","doi-asserted-by":"crossref","unstructured":"Liu, J., Liebana, D.P., Lucas, S.M.: Rolling horizon coevolutionary planning for two-player video games. In: 8th Computer Science and Electronic Engineering Conference, CEEC 2016, Colchester, UK, 28\u201330 September 2016, pp. 174\u2013179. IEEE (2016)","DOI":"10.1109\/CEEC.2016.7835909"},{"issue":"2","key":"37_CR41","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/TCIAIG.2017.2771241","volume":"10","author":"RD Gaina","year":"2018","unstructured":"Gaina, R.D., et al.: The 2016 two-player GVGAI competition. IEEE Trans. Games 10(2), 209\u2013220 (2018)","journal-title":"IEEE Trans. Games"},{"key":"37_CR42","doi-asserted-by":"crossref","unstructured":"Gaina, R.D., Devlin, S., Lucas, S.M., Perez-Liebana, D.: Rolling horizon evolutionary algorithms for general video game playing (2020)","DOI":"10.1109\/CoG47356.2020.9231587"},{"key":"37_CR43","unstructured":"Wang, H., Emmerich, M., Preuss, M., Plaat, A.: Hyper-parameter sweep on AlphaZero general. arXiv preprint arXiv:1903.08129 (2019)"},{"key":"37_CR44","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":"37_CR45","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"},{"issue":"7782","key":"37_CR46","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft ii using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"}],"container-title":["Lecture Notes in Computer Science","Parallel Problem Solving from Nature \u2013 PPSN XVI"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58115-2_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,30]],"date-time":"2021-03-30T12:39:24Z","timestamp":1617107964000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-58115-2_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030581145","9783030581152"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58115-2_37","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":"2 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PPSN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Parallel Problem Solving from Nature","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Leiden","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","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":"5 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ppsn2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ppsn2020.liacs.leidenuniv.nl\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"268","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":"99","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":"37% - 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":"2.2","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)"}}]}}