{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T12:56:10Z","timestamp":1730292970910,"version":"3.28.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,12,1]]},"DOI":"10.1109\/ricai60863.2023.10489294","type":"proceedings-article","created":{"date-parts":[[2024,4,11]],"date-time":"2024-04-11T18:46:09Z","timestamp":1712861169000},"page":"481-488","source":"Crossref","is-referenced-by-count":0,"title":["Fictitious Self-Play Reinforcement Learning with Expanding Value Estimation"],"prefix":"10.1109","author":[{"given":"Chaohao","family":"Hu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,GuangZhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunlong","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,GuangZhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weidong","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,GuangZhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongfei","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,GuangZhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Deep learning using rectified linear units (relu)","year":"2018","author":"Agarap","key":"ref1"},{"key":"ref2","first-page":"1021","article-title":"Rational and convergent learning in stochastic games","volume-title":"International Joint Conference on Artificial Intelligence","volume":"17","author":"Bowling","year":"2001"},{"issue":"1","key":"ref3","first-page":"374","article-title":"Iterative solution of games by fictitious play","volume":"13","author":"Brown","year":"1951","journal-title":"in Activity Analysis of Production and Allocation"},{"volume-title":"Equilibrium Finding for Large Adversarial Imperfect-Information Games","year":"2020","author":"Brown","key":"ref4"},{"journal-title":"Combining deep reinforcement learning and search for imperfect-information games","year":"2020","author":"Brown","key":"ref5"},{"journal-title":"Safe and nested subgame solving for imperfect-information games","year":"2017","author":"Brown","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"journal-title":"Depth-limited solving for imperfect-information games","year":"2018","author":"Brown","key":"ref8"},{"journal-title":"Optimize neural fictitious self-play in regret minimization thinking","year":"2021","author":"Chen","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2200894"},{"key":"ref11","volume-title":"The theory of learning in games","volume":"2","author":"Fudenberg","year":"1998"},{"volume-title":"Reinforcement learning from self-play in imperfect-information games","year":"2017","author":"Heinrich","key":"ref12"},{"key":"ref13","first-page":"805","article-title":"Fictitious self-play in extensive-form games","volume-title":"International Conference on Machine Learning","author":"Heinrich","year":"2015"},{"key":"ref14","first-page":"554","article-title":"Smooth UCT search in computer poker","author":"Heinrich","year":"2015","journal-title":"IJCAI"},{"journal-title":"Deep reinforcement learning from self-play in imperfect-information games","year":"2016","author":"Heinrich","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/176"},{"journal-title":"Neural fictitious self-play on elf mini-RTS","year":"2019","author":"Kawamura","key":"ref17"},{"key":"ref18","article-title":"Contributions to the Theory of Games","volume":"2","author":"Kuhn","year":"1953","journal-title":"Princeton University Press"},{"journal-title":"OpenSpiel: A framework for reinforcement learning in games","year":"2019","author":"Lanctot","key":"ref19"},{"journal-title":"A unified game-theoretic approach to multiagent reinforcement learning","year":"2017","author":"Lanctot","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1201\/9781351006620-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tg.2022.3158649"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/66"},{"journal-title":"Playing Atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"journal-title":"A generalized training approach for multiagent learning","year":"2019","author":"Muller","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2005.843878"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011158"},{"journal-title":"Actor-critic policy optimization in partially observable multiagent environments","year":"2018","author":"Srinivasan","key":"ref31"},{"journal-title":"Dream: Deep regret minimization with advantage baselines and model-free learning","year":"2020","author":"Steinberger","key":"ref32"},{"key":"ref33","volume-title":"Introduction to reinforcement learning","volume":"135","author":"Sutton","year":"1998"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511973031"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"journal-title":"Starcraft II: A new challenge for reinforcement learning","year":"2017","author":"Vinyals","key":"ref36"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3147.3165"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2539300"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2012.12.017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-020-9307-6"},{"key":"ref42","first-page":"1729","article-title":"Regret minimization in games with incomplete information","volume":"20","author":"Zinkevich","year":"2007","journal-title":"in Advances in Neural Information Processing Systems"}],"event":{"name":"2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)","start":{"date-parts":[[2023,12,1]]},"location":"Hangzhou, China","end":{"date-parts":[[2023,12,3]]}},"container-title":["2023 5th International Conference on Robotics, Intelligent Control and Artificial Intelligence (RICAI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10488913\/10488921\/10489294.pdf?arnumber=10489294","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,12]],"date-time":"2024-04-12T05:22:34Z","timestamp":1712899354000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10489294\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,1]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ricai60863.2023.10489294","relation":{},"subject":[],"published":{"date-parts":[[2023,12,1]]}}}