{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,22]],"date-time":"2025-03-22T11:00:02Z","timestamp":1742641202616},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030319779"},{"type":"electronic","value":"9783030319786"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"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":[[2019]]},"DOI":"10.1007\/978-3-030-31978-6_11","type":"book-chapter","created":{"date-parts":[[2019,9,24]],"date-time":"2019-09-24T09:03:16Z","timestamp":1569315796000},"page":"138-150","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Assessing the Potential of Classical Q-learning in General Game Playing"],"prefix":"10.1007","author":[{"given":"Hui","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Emmerich","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aske","family":"Plaat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,9,25]]},"reference":[{"issue":"2","key":"11_CR1","first-page":"62","volume":"26","author":"M Genesereth","year":"2005","unstructured":"Genesereth, M., Love, N., Pell, B.: General game playing: overview of the AAAI competition. AI Mag. 26(2), 62\u201372 (2005)","journal-title":"AI Mag."},{"key":"11_CR2","unstructured":"Love, N., Hinrichs, T., Haley, D., Schkufza, E., Genesereth, M.: General game playing: game description language specification. Stanford Technical report LG-2006-1 (2008)"},{"key":"11_CR3","unstructured":"Kaiser, D.M.: The design and implementation of a successful general game playing agent. In: International Florida Artificial Intelligence Research Society Conference, pp. 110\u2013115. AAAI Press, California (2007)"},{"issue":"2","key":"11_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2200\/S00564ED1V01Y201311AIM024","volume":"8","author":"M Genesereth","year":"2014","unstructured":"Genesereth, M., Thielscher, M.: General game playing. Synth. Lect. Artif. Intell. Mach. Learn. 8(2), 1\u2013229 (2014)","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"issue":"5","key":"11_CR5","doi-asserted-by":"publisher","first-page":"1697","DOI":"10.1093\/logcom\/exu058","volume":"26","author":"M \u015awiechowski","year":"2014","unstructured":"\u015awiechowski, M., Ma\u0144dziuk, J.: Fast interpreter for logical reasoning in general game playing. J. Logic Comput. 26(5), 1697\u20131727 (2014)","journal-title":"J. Logic Comput."},{"key":"11_CR6","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1007\/978-3-319-97310-4_20","volume-title":"PRICAI 2018: Trends in Artificial Intelligence","author":"H Wang","year":"2018","unstructured":"Wang, H., Tang, Y., Liu, J., Chen, W.: A search optimization method for rule learning in board games. In: Geng, X., Kang, B.-H. (eds.) PRICAI 2018. LNCS (LNAI), vol. 11013, pp. 174\u2013181. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-97310-4_20"},{"key":"11_CR7","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge (1998)","edition":"2"},{"issue":"1","key":"11_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCIAIG.2012.2186810","volume":"4","author":"CB Browne","year":"2012","unstructured":"Browne, C.B., Powley, E., Whitehouse, D., 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":"11_CR9","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"issue":"7587","key":"11_CR10","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D., Huang, A., Maddison, C.J., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","journal-title":"Nature"},{"key":"11_CR11","unstructured":"Mehat, J., Cazenave, T.: Monte-Carlo tree search for general game playing. Univ. Paris 8 (2008)"},{"key":"11_CR12","unstructured":"Banerjee, B., Stone, P.: General game learning using knowledge transfer. In: Veloso, M.M. (ed.) International Joint Conference on Artificial Intelligence 2007, pp. 672\u2013677 (2007)"},{"key":"11_CR13","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":"11_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-4145-2","volume-title":"Monte Carlo Methods","author":"CP Robert","year":"2004","unstructured":"Robert, C.P.: Monte Carlo Methods. Wiley, Hoboken (2004)"},{"key":"11_CR15","unstructured":"Thielscher, M.: The general game playing description language is universal. In: Toby Walsh. International Joint Conference on Artificial Intelligence 2011, vol. 22, no. 1, pp. 1107\u20131112. AAAI Press, California (2011)"},{"key":"11_CR16","volume-title":"Learning from Delayed Rewards","author":"CJCH Watkins","year":"1989","unstructured":"Watkins, C.J.C.H.: Learning from Delayed Rewards. King\u2019s College, Cambridge (1989)"},{"key":"11_CR17","unstructured":"Even-Dar, E., Mansour, Y.: Convergence of optimistic and incremental Q-learning. In: Dietterich, T.G., Becker, S., Ghahramani, Z. (eds.) Advances in Neural Information Processing Systems 2001, pp. 1499\u20131506. MIT Press, Cambridge (2001)"},{"key":"11_CR18","first-page":"1039","volume":"4","author":"J Hu","year":"2003","unstructured":"Hu, J., Wellman, M.P.: Nash Q-learning for general-sum stochastic games. J. Mach. Learn. Res. 4, 1039\u20131069 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR19","unstructured":"Silver, D., Hubert, T., Schrittwieser, J., et al.: Mastering Chess and Shogi by self-play with a general reinforcement learning algorithm. arXiv preprint arXiv:1712.01815 (2017)"},{"issue":"7676","key":"11_CR20","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., Schrittwieser, J., Simonyan, K., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"issue":"4","key":"11_CR21","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1109\/TCIAIG.2010.2088123","volume":"2","author":"J M\u00e9hat","year":"2010","unstructured":"M\u00e9hat, J., Cazenave, T.: Combining UCT and nested Monte Carlo search for single-player general game playing. IEEE Trans. Comput. Intell. AI Games 2(4), 271\u2013277 (2010)","journal-title":"IEEE Trans. Comput. Intell. AI Games"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Cazenave, T., Saffidine, A., Schofield, M.J., Thielscher, M.: Nested Monte Carlo search for two-player games. In: Schuurmans, D., Wellman, M.P. (eds.) AAAI Conference on Artificial Intelligence 2016, vol. 16, pp. 687\u2013693. AAAI Press, California (2016)","DOI":"10.1609\/aaai.v30i1.10073"},{"key":"11_CR23","unstructured":"Ruijl, B., Vermaseren, J., Plaat, A., Herik, J.: Combining simulated annealing and Monte Carlo tree search for expression simplification. In: Duval, B., Jaap van den Herik, H., Loiseau, S., Filipe, J. (eds.) Proceedings of the 6th International Conference on Agents and Artificial Intelligence 2014, vol. 1, pp. 724\u2013731. SciTePress, Set\u00fabal, Portugal (2014)"}],"container-title":["Communications in Computer and Information Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-31978-6_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,29]],"date-time":"2022-09-29T14:04:07Z","timestamp":1664460247000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-31978-6_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030319779","9783030319786"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-31978-6_11","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"25 September 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BNAIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Benelux Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"\u2018s-Hertogenbosch","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":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 November 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 November 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bnaic2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/bnaic2018.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":"31","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":"9","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":"3","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":"29% - 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":"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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}