{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:29:59Z","timestamp":1760243399137,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032080639","type":"print"},{"value":"9783032080646","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T00:00:00Z","timestamp":1760227200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-08064-6_1","type":"book-chapter","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:44:17Z","timestamp":1760219057000},"page":"3-22","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Tree Search for\u00a0Simultaneous Move Games via\u00a0Equilibrium Approximation"],"prefix":"10.1007","author":[{"given":"Ryan","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alex","family":"Olshevsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Chin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"1_CR1","unstructured":"Bakhtin, A., Wu, D., Lerer, A., Brown, N.: No-press diplomacy from scratch (2021)"},{"key":"1_CR2","unstructured":"Bakhtin, A., et al.: Mastering the game of no-press diplomacy via human-regularized reinforcement learning and planning (2022)"},{"key":"1_CR3","unstructured":"Brown, N., Bakhtin, A., Lerer, A., Gong, Q.: Combining deep reinforcement learning and search for imperfect-information games. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS \u201920, Red Hook, NY, USA. Curran Associates Inc (2020)"},{"issue":"6456","key":"1_CR4","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1126\/science.aay2400","volume":"365","author":"N Brown","year":"2019","unstructured":"Brown, N., Sandholm, T.: Superhuman AI for multiplayer poker. Science 365(6456), 885\u2013890 (2019)","journal-title":"Science"},{"key":"1_CR5","unstructured":"Daskalakis, C., Golowich, N., Zhang, K.: The complexity of Markov equilibrium in stochastic games (2022)"},{"key":"1_CR6","unstructured":"Heinrich, J., Silver, D.: Deep reinforcement learning from self-play in imperfect-information games. arXiv preprint arXiv:1603.01121 (2016)"},{"key":"1_CR7","unstructured":"Koc\u00e1k, T., Neu, G., Valko, M.: Online learning with noisy side observations. In: Gretton, A., Robert, C.C. (eds.) Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, vol.\u00a051. Proceedings of Machine Learning Research, pp. 1186\u20131194, Cadiz, Spain, 09\u201311 May 2016. PMLR (2016)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Kurach, K., et al.: A novel reinforcement learning environment. Google Research Football (2020)","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"1_CR9","first-page":"08","volume":"408","author":"M Lanctot","year":"2013","unstructured":"Lanctot, M., Lisy, V., Winands, M.: Monte Carlo tree search in simultaneous move games with applications to Goofspiel. CCIS 408, 08 (2013)","journal-title":"CCIS"},{"key":"1_CR10","unstructured":"Lanctot, M., et al.: Openspiel: a framework for reinforcement learning in games. arXiv preprint arXiv:1908.09453 (2019)"},{"key":"1_CR11","unstructured":"Lanctot, M., et al.: A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning, vol. 12 (2017)"},{"key":"1_CR12","unstructured":"Lisy, V., Kovarik, V., Lanctot, M., Bosansky, B.: Convergence of Monte Carlo tree search in simultaneous move games. In: Burges, C.J., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 26. Curran Associates, Inc. (2013)"},{"key":"1_CR13","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917, pp. 6382\u20136393, Red Hook, NY, USA. Curran Associates Inc (2017)"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Mordatch, I., Abbeel, P.: Emergence of grounded compositional language in multi-agent populations. arXiv preprint arXiv:1703.04908 (2017)","DOI":"10.1609\/aaai.v32i1.11492"},{"key":"1_CR15","unstructured":"Neller, T., Lanctot, M.: An introduction to counterfactual regret minimization (2013)"},{"key":"1_CR16","unstructured":"Neu, G.: Explore no more: improved high-probability regret bounds for non-stochastic bandits. In: Neural Information Processing Systems (2015)"},{"key":"1_CR17","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511800481","volume-title":"Algorithmic Game Theory","author":"N Nisan","year":"2007","unstructured":"Nisan, N., Roughgarden, T., Tardos, \u00c9., Vazirani, V.V.: Algorithmic Game Theory. Cambridge University Press, New York, NY, USA (2007)"},{"key":"1_CR18","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: Dy, J., Krause, A. (eds.) Proceedings of the 35th International Conference on Machine Learning, 10\u201315 Jul. Proceedings of Machine Learning Research, vol.\u00a080, pp. 4295\u20134304. PMLR (2018)"},{"key":"1_CR19","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781316779309","volume-title":"Twenty Lectures on Algorithmic Game Theory","author":"T Roughbarden","year":"2016","unstructured":"Roughbarden, T.: Twenty Lectures on Algorithmic Game Theory. Cambridge University Press, USA (2016)"},{"key":"1_CR20","unstructured":"Samvelyan, M., et al.: The starcraft multi-agent challenge. arXiv preprint arXiv:1902.04043 (2019)"},{"key":"1_CR21","unstructured":"Schrittwieser, J., et al.: Mastering atari, go, chess and shogi by planning with a learned model. arXiv preprint arXiv:1911.08265 (2019)"},{"key":"1_CR22","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550, 354 (2017)","journal-title":"Nature"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Tak, M.J.W., Lanctot, M., Winands, M.H.M.: Monte Carlo tree search variants for simultaneous move games. In: 2014 IEEE Conference on Computational Intelligence and Games, pp. 1\u20138 (2014)","DOI":"10.1109\/CIG.2014.6932889"},{"key":"1_CR24","unstructured":"Tardos, E.: Lecture 16: coarse correlated equillibrium (2020)"},{"key":"1_CR25","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in starcraft ii using multi-agent reinforcement learning. Nature 575, 350\u2013354 (2019)","journal-title":"Nature"},{"key":"1_CR26","unstructured":"Yu, C., Velu, A., Vinitsky, E., Wang, Y., Bayen, A.M., Wu, Y.: The surprising effectiveness of PPO in cooperative multi-agent games. In: Neural Information Processing Systems (2021)"},{"key":"1_CR27","unstructured":"Zhang, K., Yang, Z., Ba\u015far, T.: A selective overview of theories and algorithms, multi-agent reinforcement learning (2021)"},{"key":"1_CR28","first-page":"905","volume":"20","author":"M Zinkevich","year":"2008","unstructured":"Zinkevich, M., Johanson, M., Bowling, M., Piccione, C.: Regret minimization in games with incomplete information. Adv. Neural Inf. Process. Syst. 20, 905\u2013912 (2008)","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Game Theory and AI for Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-08064-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T21:44:33Z","timestamp":1760219073000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-08064-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"ISBN":["9783032080639","9783032080646"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-08064-6_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"12 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"GameSec","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Game Theory and AI for Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Athens","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"13 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"gamesec2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.gamesec-conf.org\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}