{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T03:58:21Z","timestamp":1743134301828,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819906161"},{"type":"electronic","value":"9789819906178"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-0617-8_11","type":"book-chapter","created":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T14:04:57Z","timestamp":1677161097000},"page":"148-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mastering \u201cGongzhu\u201d with Self-play Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5739-634X","authenticated-orcid":false,"given":"Licheng","family":"Wu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9679-3492","authenticated-orcid":false,"given":"Qifei","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4335-6635","authenticated-orcid":false,"given":"Hongming","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiali","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,24]]},"reference":[{"issue":"18","key":"11_CR1","doi-asserted-by":"publisher","first-page":"3818","DOI":"10.1063\/1.1624639","volume":"83","author":"RJ Holmes","year":"2003","unstructured":"Holmes, R.J., et al.: Efficient, deep-blue organic electrophosphorescence by guest charge trapping. Appl. Phys. Lett. 83(18), 3818\u20133820 (2003)","journal-title":"Appl. Phys. Lett."},{"issue":"7587","key":"11_CR2","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":"11_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"},{"key":"11_CR4","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/s41586-020-03051-4","volume":"588","author":"J Schrittwieser","year":"2020","unstructured":"Schrittwieser, J., et al.: Mastering Atari, Go, chess and shogi by planning with a learned model. Nature 588, 604\u2013609 (2020)","journal-title":"Nature"},{"issue":"6456","key":"11_CR5","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1126\/science.aay7774","volume":"365","author":"A Blair","year":"2019","unstructured":"Blair, A., Saffidine, A.: AI surpasses humans at six-player poker. Science 365(6456), 864\u2013865 (2019)","journal-title":"Science"},{"issue":"6337","key":"11_CR6","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1126\/science.aam6960","volume":"356","author":"M Morav\u010d\u00edk","year":"2017","unstructured":"Morav\u010d\u00edk, M., et al.: DeepStack: expert-level artificial intelligence in heads-up no-limit poker. Science 356(6337), 508\u2013513 (2017)","journal-title":"Science"},{"issue":"6374","key":"11_CR7","doi-asserted-by":"publisher","first-page":"418","DOI":"10.1126\/science.aao1733","volume":"359","author":"N Brown","year":"2018","unstructured":"Brown, N., Sandholm, T.: Superhuman AI for heads-up no-limit poker: libratus beats top professionals. Science 359(6374), 418\u2013424 (2018)","journal-title":"Science"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Jiang, Q., Li, K., Du, B.: DeltaDou: expert\/level doudizhu AI through self-play. In: Proceedings of the 28th International Joint Conference on Artificial Intelligence, pp. 1265\u20131271. Morgan Kaufmann, San Francisco (2019)","DOI":"10.24963\/ijcai.2019\/176"},{"issue":"6218","key":"11_CR9","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1126\/science.1259433","volume":"347","author":"M Bowling","year":"2015","unstructured":"Bowling, M., et al.: Heads-up limit hold\u2019em poker is solved. Science 347(6218), 145\u2013149 (2015)","journal-title":"Science"},{"key":"11_CR10","unstructured":"Brown, N., Sandholm, T., Amos, B.: Depth-limited solving for imperfect-information games. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS\u201918), pp. 7663\u20137674. Curran Associates, Red Hook, NY (2018)"},{"issue":"05","key":"11_CR11","first-page":"16","volume":"20","author":"Y Li","year":"2021","unstructured":"Li, Y., et al.: A decision model for Texas Hold\u2019em game. Software Guide 20(05), 16\u201319 (2021). In Chinses","journal-title":"Software Guide"},{"issue":"03","key":"11_CR12","first-page":"107","volume":"42","author":"Q Peng","year":"2019","unstructured":"Peng, Q., et al.: Monte Carlo tree search for \u201cDoudizhu\u201d based on hand splitting. J. Nanjing Norm. Univ. (Natural Science Edition) 42(03), 107\u2013114 (2019). In Chinese","journal-title":"J. Nanjing Norm. Univ. (Natural Science Edition)"},{"key":"11_CR13","unstructured":"Xu, F., et al.: Doudizhu strategy based on convolutional neural networks. Computer and Modernization (11), 28\u201332. In Chinese"},{"key":"11_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/978-3-030-01424-7_36","volume-title":"Artificial Neural Networks and Machine Learning \u2013 ICANN 2018","author":"S Li","year":"2018","unstructured":"Li, S., Li, S., Ding, M., Meng, K.: Research on fight the landlords\u2019 single card guessing based on deep learning. In: K\u016frkov\u00e1, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11141, pp. 363\u2013372. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01424-7_36"},{"key":"11_CR15","unstructured":"You, Y., et al.: Combinational Q-Learning for Dou Di Zhu. arXiv preprint arXiv:1901.08925 (2019)"},{"key":"11_CR16","unstructured":"Zha, D., et al.: Mastering DouDizhu with self-play deep reinforcement learning. In: Proceedings of the 38th International Conference on Machine Learning (ICML), pp. 12333\u201312344. ACM, New York, NY (2021)"},{"key":"11_CR17","unstructured":"Li, J., et al.: Suphx: mastering mahjong with deep reinforcement learning. arXiv preprint arXiv:2003.13590 (2020)"},{"issue":"4","key":"11_CR18","first-page":"1004","volume":"48","author":"M Zhang","year":"2022","unstructured":"Zhang, M., et al.: An opponent modeling and strategy integration framework for Texas Hold\u2019em AI. Acta Autom. Sin. 48(4), 1004\u20131017 (2022). In Chinese","journal-title":"Acta Autom. Sin."},{"key":"11_CR19","unstructured":"Zhou, Q., et al.: DecisionHoldem: safe depth-limited solving with diverse opponents for imperfect-information games. arXiv preprint arXiv:2201.11580 (2022)"},{"key":"11_CR20","unstructured":"Jackson, E.: Slumbot.https:\/\/www.slumbot.com\/ (2017). Last Accessed 04 Feb 2020"},{"key":"11_CR21","unstructured":"Li, K., et al.: Openholdem: an open toolkit for large-scale imperfect-information game research. arXiv preprint arXiv:2012.06168 (2020)"},{"issue":"04","key":"11_CR22","first-page":"151","volume":"12","author":"R Guo","year":"2022","unstructured":"Guo, R., et al.: Research on game strategy in two-on-one game endgame mode. Intell. Comput. Appl. 12(04), 151\u2013158 (2022). In Chinese","journal-title":"Intell. Comput. Appl."},{"key":"11_CR23","unstructured":"Yang, G., et al.: PerfectDou: dominating DouDizhu with perfect information distillation. arXiv preprint arXiv:2203.16406 (2022)"},{"issue":"1","key":"11_CR24","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3233\/ICG-210179","volume":"43","author":"M Wang","year":"2021","unstructured":"Wang, M., et al.: An efficient AI-based method to play the Mahjong game with the knowledge and game-tree searching strategy. ICGA Journal 43(1), 2\u201325 (2021)","journal-title":"ICGA Journal"},{"issue":"1","key":"11_CR25","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1049\/cit2.12031","volume":"7","author":"S Gao","year":"2022","unstructured":"Gao, S., Li, S.: Bloody Mahjong playing strategy based on the integration of deep learning and XGBoost. CAAI Trans. Intell. Technol. 7(1), 95\u2013106 (2022)","journal-title":"CAAI Trans. Intell. Technol."},{"key":"11_CR26","unstructured":"China Huapai Competition Rules Compilation Team: China Huapai Competition Rules (Trial)[M]. People\u2019s Sports Publishing House, Beijing (2009). In Chinese"}],"container-title":["Communications in Computer and Information Science","Cognitive Systems and Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-0617-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T12:09:30Z","timestamp":1684325370000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-0617-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819906161","9789819906178"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-0617-8_11","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCSIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Cognitive Systems and Signal Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fuzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 December 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 December 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccsip2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iccsip.fzu.edu.cn\/","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":"121","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":"47","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":"39% - 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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}