{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:07:19Z","timestamp":1784218039649,"version":"3.55.0"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031959721","type":"print"},{"value":"9783031959738","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-95973-8_6","type":"book-chapter","created":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T07:55:40Z","timestamp":1751270140000},"page":"86-102","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Algorithm Configuration in\u00a0Sequential Decision-Making"],"prefix":"10.1007","author":[{"given":"Luca","family":"Begnardi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bart","family":"von Meijenfeldt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingqian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Willem","family":"van Jaarsveld","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hendrik","family":"Baier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"issue":"4","key":"6_CR1","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1017\/S0269964800004101","volume":"9","author":"I Adan","year":"1995","unstructured":"Adan, I., van Eenige, M., Resing, J.: Fitting discrete distributions on the first two moments. Probab. Eng. Inf. Sci. 9(4), 623\u2013632 (1995). https:\/\/doi.org\/10.1017\/S0269964800004101","journal-title":"Probab. Eng. Inf. Sci."},{"key":"6_CR2","doi-asserted-by":"publisher","unstructured":"Adriaensen, S., et al.: Automated dynamic algorithm configuration. J. Artif. Intell. Res. 75, 1633\u20131699 (2022). https:\/\/doi.org\/10.1613\/jair.1.13922","DOI":"10.1613\/jair.1.13922"},{"key":"6_CR3","doi-asserted-by":"publisher","unstructured":"Baier, H., Kaisers, M.: Guiding multiplayer MCTS by focusing on yourself. In: IEEE Conference on Games, CoG 2020, Osaka, Japan, 24\u201327 August 2020, pp. 550\u2013557. IEEE (2020). https:\/\/doi.org\/10.1109\/COG47356.2020.9231603","DOI":"10.1109\/COG47356.2020.9231603"},{"issue":"3","key":"6_CR4","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1109\/TCIAIG.2015.2443123","volume":"8","author":"H Baier","year":"2016","unstructured":"Baier, H., Winands, M.: Time management for Monte Carlo tree search. IEEE Trans. Comput. Intell. AI Games 8(3), 301\u2013314 (2016). https:\/\/doi.org\/10.1109\/TCIAIG.2015.2443123","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"6_CR5","unstructured":"Begnardi, L., Baier, H., van Jaarsveld, W., Zhang, Y.: Deep reinforcement learning for two-sided online bipartite matching in collaborative order picking. In: Asian Conference on Machine Learning, pp. 121\u2013136. PMLR (2024)"},{"key":"6_CR6","doi-asserted-by":"publisher","unstructured":"Bhatia, A., Svegliato, J., Nashed, S.B., Zilberstein, S.: Tuning the hyperparameters of anytime planning: a metareasoning approach with deep reinforcement learning. In: Proceedings of the International Conference on Automated Planning and Scheduling, vol. 32, no. 1, pp. 556\u2013564 (2022). https:\/\/doi.org\/10.1609\/icaps.v32i1.19842","DOI":"10.1609\/icaps.v32i1.19842"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Biedenkapp, A., Bozkurt, H.F., Eimer, T., Hutter, F., Lindauer, M.: Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework. Santiago de Compostela (2020)","DOI":"10.3233\/FAIA200122"},{"issue":"1","key":"6_CR8","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/S13218-010-0080-9","volume":"25","author":"H Finnsson","year":"2011","unstructured":"Finnsson, H., Bj\u00f6rnsson, Y.: Cadiaplayer: search-control techniques. K\u00fcnstliche Intell. 25(1), 9\u201316 (2011). https:\/\/doi.org\/10.1007\/S13218-010-0080-9","journal-title":"K\u00fcnstliche Intell."},{"key":"6_CR9","doi-asserted-by":"publisher","unstructured":"Gelly, S., Silver, D.: Combining online and offline knowledge in UCT. In: Ghahramani, Z. (ed.) Machine Learning, Proceedings of the Twenty-Fourth International Conference (ICML 2007), Corvallis, Oregon, USA, 20\u201324 June 2007. ACM International Conference Proceeding Series, vol.\u00a0227, pp. 273\u2013280. ACM (2007). https:\/\/doi.org\/10.1145\/1273496.1273531","DOI":"10.1145\/1273496.1273531"},{"key":"6_CR10","unstructured":"Huberman, B.J.: A program to play chess end games. Ph.D. thesis, Stanford University, USA (1968). https:\/\/searchworks.stanford.edu\/view\/2190328"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Kocsis, L., Szepesv\u00e1ri, C.: Bandit based Monte-Carlo planning. In: F\u00fcrnkranz, J., Scheffer, T., Spiliopoulou, M. (eds.) ECML 2006. LNCS (LNAI), vol. 4212, pp. 282\u2013293. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11871842_29","DOI":"10.1007\/11871842_29"},{"key":"6_CR12","doi-asserted-by":"publisher","unstructured":"Lan, L.C., Wu, T.R., Wu, I.C., Hsieh, C.J.: Learning to stop: dynamic simulation Monte-Carlo tree search. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 1, pp. 259\u2013267 (2021). https:\/\/doi.org\/10.1609\/aaai.v35i1.16100","DOI":"10.1609\/aaai.v35i1.16100"},{"key":"6_CR13","unstructured":"Lanctot, M., et\u00a0al.: Openspiel: a framework for reinforcement learning in games. arXiv preprint arXiv:1908.09453 (2019)"},{"key":"6_CR14","doi-asserted-by":"publisher","unstructured":"Reijnen, R., Zhang, Y., Lau, H.C., Bukhsh, Z.: Online control of adaptive large neighborhood search using deep reinforcement learning. In: Proceedings of the International Conference on Automated Planning and Scheduling, vol. 34, pp. 475\u2013483 (2024). https:\/\/doi.org\/10.1609\/icaps.v34i1.31507","DOI":"10.1609\/icaps.v34i1.31507"},{"key":"6_CR15","first-page":"425","volume":"75","author":"E Schede","year":"2022","unstructured":"Schede, E.: A survey of methods for automated algorithm configuration. J. Arti. Intell. Res. 75, 425\u2013487 (2022)","journal-title":"J. Arti. Intell. Res."},{"key":"6_CR16","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal Policy Optimization Algorithms (2017). arXiv:1707.06347"},{"issue":"6419","key":"6_CR17","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"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Silver, D., et\u00a0al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","DOI":"10.1038\/nature24270"},{"issue":"2","key":"6_CR19","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1109\/TG.2018.2884768","volume":"12","author":"CF Sironi","year":"2020","unstructured":"Sironi, C.F., Liu, J., Winands, M.: Self-adaptive Monte Carlo tree search in general game playing. IEEE Trans. Games 12(2), 132\u2013144 (2020). https:\/\/doi.org\/10.1109\/TG.2018.2884768","journal-title":"IEEE Trans. Games"},{"key":"6_CR20","doi-asserted-by":"publisher","unstructured":"Speck, D., Biedenkapp, A., Hutter, F., Mattm\u00fcller, R., Lindauer, M.: Learning heuristic selection with dynamic algorithm configuration. In: Proceedings of the International Conference on Automated Planning and Scheduling, vol. 31, pp. 597\u2013605 (2021). https:\/\/doi.org\/10.1609\/icaps.v31i1.16008","DOI":"10.1609\/icaps.v31i1.16008"},{"key":"6_CR21","doi-asserted-by":"publisher","unstructured":"Xu, Z., et al.: APPLR: adaptive planner parameter learning from reinforcement. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 6086\u20136092 (2021). https:\/\/doi.org\/10.1109\/ICRA48506.2021.9561647","DOI":"10.1109\/ICRA48506.2021.9561647"},{"key":"6_CR22","doi-asserted-by":"crossref","unstructured":"Ye, W., Abbeel, P., Gao, Y.: Spending thinking time wisely: accelerating MCTS with virtual expansions. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 12211\u201312224. Curran Associates, Inc. (2022)","DOI":"10.52202\/068431-0887"}],"container-title":["Lecture Notes in Computer Science","Integration of Constraint Programming, Artificial Intelligence, and Operations Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-95973-8_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:41:50Z","timestamp":1784216510000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-95973-8_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031959721","9783031959738"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-95973-8_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"29 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CPAIOR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cpaior2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/cpaior2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}