{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T03:04:43Z","timestamp":1773371083214,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":28,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819785018","type":"print"},{"value":"9789819785025","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-8502-5_10","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:03:04Z","timestamp":1730383384000},"page":"130-143","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Asymmetric Game Theoretic Learning Model"],"prefix":"10.1007","author":[{"given":"Qiyue","family":"Yin","sequence":"first","affiliation":[]},{"given":"Tongtong","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Xueou","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Kaiqi","family":"Huang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"10_CR1","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., Guez, A., Sifre, L., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016)","journal-title":"Nature"},{"key":"10_CR2","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., Antonoglou, I., Huang, A., et al.: Mastering the game of go without human knowledge. Nature 550, 354\u2013359 (2017)","journal-title":"Nature"},{"key":"10_CR3","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362, 1140\u20131144 (2018)","journal-title":"Science"},{"key":"10_CR4","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., Babuschkin, I., Czarnecki, W.M., Mathieu, M., Dudzik, A., et al.: Grandmaster level in starcraft ii using multiagent reinforcement learning. Nature 575, 350\u2013354 (2019)","journal-title":"Nature"},{"key":"10_CR5","unstructured":"Berner, C., Brockman, G., Chan, B., Cheung, V., Dbiak, P., et al.: Dota 2 with large scale deep reinforcement learning (2019). arXiv:1912.06680v1"},{"issue":"5","key":"10_CR6","first-page":"913","volume":"49","author":"QY Yin","year":"2023","unstructured":"Yin, Q.Y., Zhao, M.J., Ni, W.C., Zhang, J.G., Huang, K.Q.: Intelligent decision making technology and challenge of wargame. Acta Autom. Sin. 49(5), 913\u2013928 (2023)","journal-title":"Acta Autom. Sin."},{"key":"10_CR7","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11633-022-1384-6","volume":"20","author":"QY Yin","year":"2023","unstructured":"Yin, Q.Y., Yang, J., Ni, W.C., Liang, B., Huang, K.Q.: AI in human-computer gaming: techniques, challenges and opportunities. Mach. Intell. Res. 20, 299\u2013319 (2023)","journal-title":"Mach. Intell. Res."},{"issue":"6","key":"10_CR8","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1542\/peds.112.6.1231","volume":"112","author":"J Juvonen","year":"2003","unstructured":"Juvonen, J., Graham, S., Schuster, M.A.: Bullying among young adolescents: the strong, the weak, and the troubled. Pediatrics 112(6), 1231\u20131237 (2003)","journal-title":"Pediatrics"},{"key":"10_CR9","doi-asserted-by":"publisher","DOI":"10.7765\/9781847792976","volume-title":"Romania and the European Union: How the Weak Vanquished the Strong","author":"T Gallagher","year":"2013","unstructured":"Gallagher, T.: Romania and the European Union: How the Weak Vanquished the Strong. Manchester University Press, Romania and the European Union (2013)"},{"key":"10_CR10","unstructured":"Zhou, L., Yin, Q. Y., Huang, K. Q.: Game-theoretic learning in human-computer gaming. Chin. J. Comput. (2022)"},{"key":"10_CR11","unstructured":"Fudenberg, D., Tirole, J.: Game Theory. MIT Press (1991)"},{"key":"10_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1454-4","author":"QY Yin","year":"2024","unstructured":"Yin, Q.Y., Yu, T.T., Shen, S.Q., et al.: Distributed deep reinforcement learning: a survey and a multi-player multi-agent learning toolbox. Mach. Intell. Res. (2024). https:\/\/doi.org\/10.1007\/s11633-023-1454-4","journal-title":"Mach. Intell. Res."},{"issue":"10","key":"10_CR13","doi-asserted-by":"publisher","first-page":"2234","DOI":"10.3390\/math11102234","volume":"11","author":"W Long","year":"2023","unstructured":"Long, W., Hou, T., Wei, X., Yan, S., et al.: A survey on population-based deep reinforcement learning. Mathematics 11(10), 2234 (2023)","journal-title":"Mathematics"},{"key":"10_CR14","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 nolimit poker: libratus beats top professionals. Science 359, 418\u2013424 (2018)","journal-title":"Science"},{"key":"10_CR15","unstructured":"Engstrom, L., Ilyas, A., Santurkar, S., et al.: Implementation matters in deep RL: a case study on PPO and TRPO. In: International Conference on Learning Representations (2019)"},{"key":"10_CR16","unstructured":"Yu, C., Velu, A., Vinitsky, E., et al.: The surprising effectiveness of ppo in cooperative, multi-agent games (2021). arXiv:2103.01955"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Ly, A., Dazeley, R., Vamplew, P., et al.: Elastic step DQN: a novel multi-step algorithm to alleviate overestimation in deep Q-networks 576, 127170 (2024)","DOI":"10.1016\/j.neucom.2023.127170"},{"issue":"14s","key":"10_CR18","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1145\/3596444","volume":"55","author":"M Landers","year":"2023","unstructured":"Landers, M., Doryab, A.: Deep reinforcement leanring verification: a survey. ACM Comput. Surv. 55(14s), 330 (2023)","journal-title":"ACM Comput. Surv."},{"key":"10_CR19","unstructured":"Lanctot, M., Zambaldi, V., Gruslys, A., et al.: A unified game-theoretic approach to multiagent reinforcement learning. Adv. Neural Inf. Process. Syst. (2017)"},{"issue":"5","key":"10_CR20","first-page":"1","volume":"15","author":"L Zhang","year":"2021","unstructured":"Zhang, L., Chen, Y., Wang, W., et al.: A Monte Carlo neural fictitious self-play approach to approximate Nash equilibrium in imperfect-information dynamic games. Front. Comp. Sci. 15(5), 1\u201314 (2021)","journal-title":"Front. Comp. Sci."},{"key":"10_CR21","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1613\/jair.4477","volume":"51","author":"B Bosansky","year":"2014","unstructured":"Bosansky, B., Kiekintveld, C., Lisy, V., et al.: An exact double-oracle algorithm for zero-sum extensive-form games with imperfect information. J. Artif. Intell. Res. 51, 829\u2013866 (2014)","journal-title":"J. Artif. Intell. Res."},{"key":"10_CR22","unstructured":"Chen, J., Xie, W., Zhang, W., et al.: Offline fictitious self-play for competitive games (2024). arXiv:2403.00841"},{"key":"10_CR23","unstructured":"Ye, D., Chen, G., Zhang, W., Chen, S., Yuan, B., et al.: Towards playing full MOBA games with deep reinforcement learning. Neural Inf. Process. Syst. (2020)"},{"key":"10_CR24","unstructured":"Zha, D., Xie, J., Ma, W., Zhang, S., Lian, X., et al.: Douzero: mastering Doudizhu with self-play deep reinforcement learning. In: International Conference on Machine Learning (2021)"},{"key":"10_CR25","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1126\/science.aau6249","volume":"364","author":"M Jaderberg","year":"2019","unstructured":"Jaderberg, M., Czarnecki, W.M., Dunning, I., Marris, L., Lever, G., et al.: Human-level performance in 3D multiplayer games with populationbased reinforcement learning. Science 364, 859\u2013865 (2019)","journal-title":"Science"},{"key":"10_CR26","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1038\/s41586-021-04357-7","volume":"602","author":"PR Wurman","year":"2022","unstructured":"Wurman, P.R., Barrett, S., Kawamoto, K., et al.: Outracing champion Gran Turismo drivers with deep reinforcement learning. Nature 602, 223\u2013228 (2022)","journal-title":"Nature"},{"key":"10_CR27","unstructured":"Domingo-Enrich, C., Jelassi, S., Mensch, A., Rotskoff, G., Bruna, J.: A mean-field analysis of two-player zero-sum games. Adv. Neural Inf. Process. Syst. (2022)"},{"issue":"1","key":"10_CR28","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1137\/070699652","volume":"39","author":"C Daskalakis","year":"2009","unstructured":"Daskalakis, C., Goldberg, P.W., Papadimitriou, C.H.: The complexity of computing a Nash equilibrium. SIAM J. Comput. 39(1), 195\u2013259 (2009)","journal-title":"SIAM J. Comput."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8502-5_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T14:17:37Z","timestamp":1730384257000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8502-5_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819785018","9789819785025"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8502-5_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","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":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}