{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,17]],"date-time":"2025-04-17T20:30:40Z","timestamp":1744921840230,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":25,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785049"},{"type":"electronic","value":"9789819785056"}],"license":[{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T00:00:00Z","timestamp":1730937600000},"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\/978-981-97-8505-6_32","type":"book-chapter","created":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:01:55Z","timestamp":1730930515000},"page":"451-465","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["More Like Real World Game Challenge for Partially Observable Multi-agent Cooperation"],"prefix":"10.1007","author":[{"given":"Xueou","family":"Feng","sequence":"first","affiliation":[]},{"given":"Meng","family":"Yao","sequence":"additional","affiliation":[]},{"given":"Shengqi","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Qiyue","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Jun","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"32_CR1","unstructured":"Baker, B., Kanitscheider, I., Markov, T., Wu, Y., Powell, G., McGrew, B., Mordatch, I.: Emergent tool use from multi-agent interaction. In: Machine Learning. Cornell University (2019)"},{"key":"32_CR2","unstructured":"Berner, C., Brockman, G., Chan, B., Cheung, V., Debiak, P., Dennison, C., Farhi, D., Fischer, Q., Hashme, S., Hesse, C., et\u00a0al.: Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680 (2019)"},{"key":"32_CR3","unstructured":"Ellis, B., Cook, J., Moalla, S., et\u00a0al.: Smacv2: An improved benchmark for cooperative multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 37567\u201337593 (2023)"},{"key":"32_CR4","unstructured":"Halpern, J.Y.: Computer science and game theory: A brief survey. arXiv preprint cs\/0703148 (2007)"},{"key":"32_CR5","unstructured":"Huang, J.t., Li, E.J., Lam, M.H., et\u00a0al.: How far are we on the decision-making of llms? evaluating llms\u2019 gaming ability in multi-agent environments. arXiv:2403.11807 (2024)"},{"key":"32_CR6","unstructured":"Jia, H., Hu, Y., Chen, Y., Ren, C., Lv, T., Fan, C., Zhang, C.: Fever basketball: A complex, flexible, and asynchronized sports game environment for multi-agent reinforcement learning. arXiv preprint arXiv:2012.03204 (2020)"},{"key":"32_CR7","doi-asserted-by":"crossref","unstructured":"Kurach, K., Raichuk, A., Stanczyk, P., Zajac, M., Bachem, O., Espeholt, L., Riquelme, C., Vincent, D., Michalski, M., Bousquet, O., et\u00a0al.: Google research football: A novel reinforcement learning environment, pp. 4501\u20134510 (2020)","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"32_CR8","unstructured":"Leibo, J.Z., Zambaldi, V., Lanctot, M., Marecki, J., Graepel, T.: Multi-agent reinforcement learning in sequential social dilemmas. arXiv preprint arXiv:1702.03037 (2017)"},{"key":"32_CR9","unstructured":"Liu, Z., Chen, G., Zhang, W., et\u00a0al.: Towards playing full moba games with deep reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 621\u2013632 (2020)"},{"key":"32_CR10","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments, pp. 6382\u20136393 (2017)"},{"key":"32_CR11","doi-asserted-by":"crossref","unstructured":"Ning, Z., Xie, L.: A survey on multi-agent reinforcement learning and its application. In: Journal of Automation and Intelligence (2024)","DOI":"10.1016\/j.jai.2024.02.003"},{"key":"32_CR12","doi-asserted-by":"crossref","unstructured":"Oliehoek, F.A., Amato, C.: A concise introduction to decentralized POMDPs. Springer (2016)","DOI":"10.1007\/978-3-319-28929-8"},{"key":"32_CR13","doi-asserted-by":"publisher","first-page":"13677","DOI":"10.1007\/s10489-022-04105-y","volume":"53","author":"A Oroojlooy","year":"2023","unstructured":"Oroojlooy, A., Hajinezhzd, D.: A review of cooperative multi-agent deep reinforcement learning. Appl. Intell. 53, 13677\u201313722 (2023)","journal-title":"Appl. Intell."},{"key":"32_CR14","unstructured":"Peng, B., Rashid, T., Schroeder\u00a0de Witt, C., Kamienny, P.A., Torr, P., B\u00f6hmer, W., Whiteson, S.: Facmac: Factored multi-agent centralised policy gradients. Adv. Neural Inf. Process. Syst. 34, 12208\u201312221 (2021)"},{"key":"32_CR15","unstructured":"Rashid, T., Samvelyan, M., Schroeder, C., Farquhar, G., Foerster, J., Whiteson, S.: Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4295\u20134304. PMLR (2018)"},{"key":"32_CR16","unstructured":"Resnick, C., Eldridge, W., Ha, D., Britz, D., Foerster, J., Togelius, J., Cho, K., Bruna, J.: Pommerman: A multi-agent playground. arXiv preprint arXiv:1809.07124 (2018)"},{"key":"32_CR17","unstructured":"Samvelyan, M., Rashid, T., De\u00a0Witt, C.S., Farquhar, G., Nardelli, N., Rudner, T.G., Hung, C.M., Torr, P.H., Foerster, J., Whiteson, S.: The starcraft multi-agent challenge, pp. 2186\u20132188 (2019)"},{"key":"32_CR18","first-page":"20","volume":"2","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., Babuschkin, I., Chung, J., Mathieu, M., Jaderberg, M., Czarnecki, W.M., Dudzik, A., Huang, A., Georgiev, P., Powell, R., et al.: Alphastar: Mastering the real-time strategy game starcraft ii. DeepMind Blog 2, 20 (2019)","journal-title":"DeepMind Blog"},{"key":"32_CR19","doi-asserted-by":"publisher","first-page":"5023","DOI":"10.1007\/s10462-022-10299-x","volume":"56","author":"A Wong","year":"2023","unstructured":"Wong, A., Back, T., Kononova, A.V., Plaat, A.: Deep multiagent reinforcement learning: challenges and directions. Artif. Intell. Rev. 56, 5023\u20135056 (2023)","journal-title":"Artif. Intell. Rev."},{"key":"32_CR20","unstructured":"Yang, Y., Luo, R., Li, M., Zhou, M., Zhang, W., Wang, J.: Mean field multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 5571\u20135580. PMLR (2018)"},{"issue":"3","key":"32_CR21","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11633-022-1384-6","volume":"20","author":"Q Yin","year":"2023","unstructured":"Yin, Q., Yang, J., Huang, K., Zhao, M., Ni, W., et al.: Ai in human-computer gaming: techniques, challenges and opportunities. Mach. Intell. Res. 20(3), 299\u2013317 (2023)","journal-title":"Mach. Intell. Res."},{"issue":"3","key":"32_CR22","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1007\/s11633-023-1454-4","volume":"21","author":"Q Yin","year":"2024","unstructured":"Yin, Q., Yu, T., Shen, S., Yang, J., Zhao, M., Huang, K., Liang, B., Wang, L.: Distributed deep reinforcement learning: A survey and a multi-player multi-agent learning toolbox. Mach. Intell. Res. 21(3), 411\u2013430 (2024)","journal-title":"Mach. Intell. Res."},{"issue":"5","key":"32_CR23","first-page":"913","volume":"49","author":"Q Yin","year":"2023","unstructured":"Yin, Q., Zhao, M., Ni, W., Zhang, J., Huang, K.: Intelligent decision making technology and challenge of wargame. Acta Autom. Sinica 49(5), 913\u2013928 (2023)","journal-title":"Acta Autom. Sinica"},{"key":"32_CR24","unstructured":"Zha, D., Xie, J., Ma, W., Zhang, S., Lian, X., Hu, X., Liu, J.: Douzero: Mastering doudizhu with self-play deep reinforcement learning. In: International Conference on Machine Learning, pp. 12333\u201312344. PMLR (2021)"},{"key":"32_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, H., Feng, S., Liu, C., Ding, Y., Zhu, Y., Zhou, Z., Zhang, W., Yu, Y., Jin, H., Li, Z.: Cityflow: A multi-agent reinforcement learning environment for large scale city traffic scenario. In: The World Wide Web Conference, pp. 3620\u20133624 (2019)","DOI":"10.1145\/3308558.3314139"}],"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\/978-981-97-8505-6_32","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T22:07:10Z","timestamp":1730930830000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8505-6_32"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,7]]},"ISBN":["9789819785049","9789819785056"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8505-6_32","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,7]]},"assertion":[{"value":"7 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"}}]}}