{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,30]],"date-time":"2025-08-30T00:07:13Z","timestamp":1756512433301,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,22]],"date-time":"2023-12-22T00:00:00Z","timestamp":1703203200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"the National Natural Science Foundation of China","award":["No.U19B2044 and No.61836011"],"award-info":[{"award-number":["No.U19B2044 and No.61836011"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,22]]},"DOI":"10.1145\/3639631.3639632","type":"proceedings-article","created":{"date-parts":[[2024,2,16]],"date-time":"2024-02-16T06:08:33Z","timestamp":1708063713000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Neural Future-Dependent Online Mirror Descent"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4927-0898","authenticated-orcid":false,"given":"Kezhe","family":"Xie","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4262-639X","authenticated-orcid":false,"given":"Weiming","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2332-3959","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,2,16]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Conference on Learning Theory.","author":"Abernethy Jacob\u00a0Duncan","year":"2008","unstructured":"Jacob\u00a0Duncan Abernethy, Elad Hazan, and Alexander Rakhlin. 2008. An efficient algorithm for bandit linear optimization. In Conference on Learning Theory."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(02)00231-6"},{"key":"e_1_3_2_1_3_1","volume-title":"International conference on machine learning. PMLR, 793\u2013802","author":"Brown Noam","year":"2019","unstructured":"Noam Brown, Adam Lerer, Sam Gross, and Tuomas Sandholm. 2019. Deep counterfactual regret minimization. In International conference on machine learning. PMLR, 793\u2013802."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10056"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11370"},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR","author":"Farina Gabriele","year":"2019","unstructured":"Gabriele Farina, Christian Kroer, Noam Brown, and Tuomas Sandholm. 2019. Stable-predictive optimistic counterfactual regret minimization. In International conference on machine learning. PMLR, 1853\u20131862."},{"key":"e_1_3_2_1_7_1","volume-title":"Optimistic regret minimization for extensive-form games via dilated distance-generating functions. Advances in neural information processing systems 32","author":"Farina Gabriele","year":"2019","unstructured":"Gabriele Farina, Christian Kroer, and Tuomas Sandholm. 2019. Optimistic regret minimization for extensive-form games via dilated distance-generating functions. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Machine Learning. PMLR, 3018\u20133028","author":"Farina Gabriele","year":"2020","unstructured":"Gabriele Farina, Christian Kroer, and Tuomas Sandholm. 2020. Stochastic regret minimization in extensive-form games. In International Conference on Machine Learning. PMLR, 3018\u20133028."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1561\/9781680831719"},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 805\u2013813","author":"Heinrich Johannes","year":"2015","unstructured":"Johannes Heinrich, Marc Lanctot, and David Silver. 2015. Fictitious self-play in extensive-form games. In International conference on machine learning. PMLR, 805\u2013813."},{"key":"e_1_3_2_1_11_1","volume-title":"Deep reinforcement learning from self-play in imperfect-information games. arXiv preprint arXiv:1603.01121","author":"Heinrich Johannes","year":"2016","unstructured":"Johannes Heinrich and David Silver. 2016. Deep reinforcement learning from self-play in imperfect-information games. arXiv preprint arXiv:1603.01121 (2016)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.1100.0452"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tcs.2019.11.015"},{"key":"e_1_3_2_1_14_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma P","year":"2014","unstructured":"Diederik\u00a0P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1336-7"},{"key":"e_1_3_2_1_16_1","volume-title":"Monte Carlo sampling for regret minimization in extensive games. Advances in neural information processing systems 22","author":"Lanctot Marc","year":"2009","unstructured":"Marc Lanctot, Kevin Waugh, Martin Zinkevich, and Michael Bowling. 2009. Monte Carlo sampling for regret minimization in extensive games. Advances in neural information processing systems 22 (2009)."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Machine Learning. PMLR, 13717\u201313745","author":"Liu Weiming","year":"2022","unstructured":"Weiming Liu, Huacong Jiang, Bin Li, and Houqiang Li. 2022. Equivalence analysis between counterfactual regret minimization and online mirror descent. In International Conference on Machine Learning. PMLR, 13717\u201313745."},{"key":"e_1_3_2_1_18_1","volume-title":"Model-free neural counterfactual regret minimization with bootstrap learning","author":"Liu Weiming","year":"2022","unstructured":"Weiming Liu, Bin Li, and Julian Togelius. 2022. Model-free neural counterfactual regret minimization with bootstrap learning. IEEE Transactions on Games (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Linjian Meng Zhenxing Ge Pinzhuo Tian Bo An and Yang Gao. 2023. Deep FTRL-ORW: An Efficient Deep Reinforcement Learning Algorithm for Solving Imperfect Information Extensive-Form Games. (2023).","DOI":"10.1609\/aaai.v37i5.25722"},{"key":"e_1_3_2_1_20_1","volume-title":"Non-cooperative games. Annals of mathematics","author":"Nash John","year":"1951","unstructured":"John Nash. 1951. Non-cooperative games. Annals of mathematics (1951), 286\u2013295."},{"key":"e_1_3_2_1_21_1","volume-title":"Bayes","author":"Southey Finnegan","year":"2012","unstructured":"Finnegan Southey, Michael\u00a0P Bowling, Bryce Larson, Carmelo Piccione, Neil Burch, Darse Billings, and Chris Rayner. 2012. Bayes\u2019 bluff: Opponent modelling in poker. arXiv preprint arXiv:1207.1411 (2012)."},{"key":"e_1_3_2_1_22_1","volume-title":"DREAM: Deep regret minimization with advantage baselines and model-free learning. arXiv preprint arXiv:2006.10410","author":"Steinberger Eric","year":"2020","unstructured":"Eric Steinberger, Adam Lerer, and Noam Brown. 2020. DREAM: Deep regret minimization with advantage baselines and model-free learning. arXiv preprint arXiv:2006.10410 (2020)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3147.3165"},{"key":"e_1_3_2_1_24_1","volume-title":"Regret minimization in games with incomplete information. Advances in neural information processing systems 20","author":"Zinkevich Martin","year":"2007","unstructured":"Martin Zinkevich, Michael Johanson, Michael Bowling, and Carmelo Piccione. 2007. Regret minimization in games with incomplete information. Advances in neural information processing systems 20 (2007)."}],"event":{"name":"ACAI 2023: 2023 6th International Conference on Algorithms, Computing and Artificial Intelligence","acronym":"ACAI 2023","location":"Sanya China"},"container-title":["2023 6th International Conference on Algorithms Computing and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639631.3639632","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3639631.3639632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,29]],"date-time":"2025-08-29T17:40:48Z","timestamp":1756489248000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3639631.3639632"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,22]]},"references-count":24,"alternative-id":["10.1145\/3639631.3639632","10.1145\/3639631"],"URL":"https:\/\/doi.org\/10.1145\/3639631.3639632","relation":{},"subject":[],"published":{"date-parts":[[2023,12,22]]},"assertion":[{"value":"2024-02-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}