{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T09:44:22Z","timestamp":1766137462506,"version":"3.37.3"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:00:00Z","timestamp":1630454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Planning and Learning to Act in Systems of Multiple Agents","award":["19-CE23-0018-01"],"award-info":[{"award-number":["19-CE23-0018-01"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2021,9]]},"DOI":"10.1109\/tg.2020.3005214","type":"journal-article","created":{"date-parts":[[2020,6,26]],"date-time":"2020-06-26T22:23:08Z","timestamp":1593210188000},"page":"239-248","source":"Crossref","is-referenced-by-count":4,"title":["Heuristic Search Value Iteration for Zero-Sum Stochastic Games"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5072-5857","authenticated-orcid":false,"given":"Olivier","family":"Buffet","sequence":"first","affiliation":[]},{"given":"Jilles","family":"Dibangoye","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9805-8291","authenticated-orcid":false,"given":"Abdallah","family":"Saffidine","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3401-4649","authenticated-orcid":false,"given":"Vincent","family":"Thomas","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-35706-5_23"},{"key":"ref32","first-page":"698","article-title":"Learning strategies in games by anticipation","author":"meyer","year":"0","journal-title":"Proc 15th Int Joint Conf Artif Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"journal-title":"Neurodynamic Programming","year":"1996","author":"bertsekas","key":"ref30"},{"key":"ref37","article-title":"On Bellman's optimality principle for zs-POSGs","volume":"abs 2006 16395","author":"buffet","year":"0","journal-title":"Comput Res Repository"},{"key":"ref36","article-title":"Evolving strategies for the game footsteps","author":"morris","year":"0","journal-title":"Proc UK Workshop Comput Intell"},{"key":"ref35","first-page":"6933","article-title":"$\\rho$-POMDPs have Lipschitz-continuous $\\epsilon$-optimal value functions","author":"fehr","year":"0","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref34","first-page":"1233","article-title":"Faster heuristic search algorithms for planning with uncertainty and full feedback","author":"bonet","year":"0","journal-title":"Proc 18th Int Joint Conf Artif Intell"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v39i1.2777"},{"key":"ref11","first-page":"558","article-title":"Heuristic search value iteration for one-sided partially observable stochastic games","author":"hor\u00e1k","year":"0","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33012029"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102423"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF01415989"},{"key":"ref15","first-page":"310","article-title":"A generalized reinforcement learning model: Convergence and applications","author":"littman","year":"0","journal-title":"Proc 13th Int Conf Mach Learn"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"},{"key":"ref17","first-page":"283","article-title":"Value function approximation in zero-sum Markov games","author":"lagoudakis","year":"0","journal-title":"Proc 18th Conf Uncertainty Artif Intell"},{"key":"ref18","first-page":"1860","article-title":"Softened approximate policy iteration for Markov games","volume":"48","author":"p\u00e9rolat","year":"0","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref19","first-page":"556","article-title":"Alpha-Beta pruning for games with simultaneous moves","author":"saffidine","year":"0","journal-title":"Proc 26th AAAI Conf Artif Intell"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1515\/9781400882014-002"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(01)00106-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref3","first-page":"12","article-title":"Labeled RTDP: Improving the convergence of real-time dynamic programming","author":"bonet","year":"0","journal-title":"Proc 13th Int Conf Autom Planning Scheduling"},{"key":"ref6","first-page":"576","article-title":"MAA*: A heuristic search algorithm for solving decentralized POMDPs","author":"szer","year":"0","journal-title":"Proc 21st Conf Uncertainty Artif Intell"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1090\/S0002-9904-1954-09848-8"},{"key":"ref5","first-page":"542","article-title":"Point-based POMDP algorithms: Improved analysis and implementation","author":"smith","year":"0","journal-title":"Proc 21st Conf Uncertainty Artif Intell"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4623"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1789"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/9.286259"},{"journal-title":"Artificial Intelligence A Modern Approach","year":"2010","author":"russell","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2016.03.005"},{"key":"ref22","first-page":"67","article-title":"Nested-greedy search for adversarial real-time games","author":"moraes","year":"0","journal-title":"Proc 14th AAAI Conf Artif Intell Interact Digit Entertainment"},{"key":"ref21","first-page":"112","article-title":"Fast heuristic search for RTS game combat scenarios","author":"churchill","year":"0","journal-title":"Proc 8th AAAI Conf Artif Intell Interact Digit Entertainment"},{"article-title":"Probabilistic planning for robotic exploration","year":"2007","author":"smith","key":"ref24"},{"journal-title":"Encyclopedia of Database Systems","year":"2009","author":"solal","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF01448847"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1515\/9781400884087-007"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/9538938\/09127109.pdf?arnumber=9127109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:55:55Z","timestamp":1641988555000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9127109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9]]},"references-count":37,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tg.2020.3005214","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2021,9]]}}}