{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T06:06:15Z","timestamp":1749017175777,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010615","type":"proceedings-article","created":{"date-parts":[[2015,1,19]],"date-time":"2015-01-19T21:48:03Z","timestamp":1421704083000},"page":"1-8","source":"Crossref","is-referenced-by-count":5,"title":["An analysis of optimistic, best-first search for minimax sequential decision making"],"prefix":"10.1109","author":[{"given":"Lucian","family":"Busoniu","sequence":"first","affiliation":[]},{"given":"Remi","family":"Munos","sequence":"additional","affiliation":[]},{"given":"Elod","family":"Pall","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1201\/9781420049503-c37"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00096-8"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"journal-title":"Predictive Control with Constraints","year":"2002","author":"maciejowski","key":"ref13"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1609\/icaps.v21i1.13484","article-title":"Sample-based planning for continuous action Markov decision processes","author":"mansley","year":"2011","journal-title":"Proceedings 21st International Conference on Automated Planning and Scheduling"},{"key":"ref15","first-page":"783","article-title":"Optimistic optimization of a deterministic function without the knowledge of its smoothness","author":"munos","year":"2011","journal-title":"Advances in Neural Information Processing Systems 24"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1561\/2200000038"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(82)90034-0"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/358589.358616"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00126-3"},{"key":"ref4","article-title":"Optimistic planning for continuous–action deterministic systems","author":"bu?oniu","year":"2013","journal-title":"2013 IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL-13)"},{"key":"ref3","first-page":"477","article-title":"Open loop optimistic planning","author":"bubeck","year":"2010","journal-title":"Proceedings 23rd Annual Conference on Learning Theory (COLT-10)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967375"},{"key":"ref5","first-page":"182","article-title":"Optimistic planning for Markov decision processes","volume":"22","author":"bu?oniu","year":"2012","journal-title":"Proceedings 15th International Conference on Artificial Intelligence and Statistics (AISTATS-12) Ser JMLR Workshop and Conference Proceedings"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/0004-3702(75)90019-3","article-title":"An analysis of alpha-beta pruning","volume":"6","author":"knuth","year":"1975","journal-title":"Artificial Intelligence"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89722-4_12"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(79)90003-1"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"223","DOI":"10.3934\/mbe.2004.1.223","article-title":"Dynamic multidrug therapies for HIV: Optimal and STI control approaches","volume":"1","author":"adams","year":"2004","journal-title":"Mathematical Biosciences and Engineering"},{"key":"ref9","first-page":"282","article-title":"Bandit based Monte-Carlo planning","author":"kocsis","year":"2006","journal-title":"Proceedings 17th European Conference on Machine Learning (ECML-06)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1023\/A:1016246616462"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v24i1.7689","article-title":"Integrating sample-based planning and model-based reinforcement learning","author":"walsh","year":"2010","journal-title":"Proceedings 24th AAAI Conference on Artificial Intelligence (AAAI-10)"}],"event":{"name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2014,12,9]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2014,12,12]]}},"container-title":["2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7000183\/7010603\/07010615.pdf?arnumber=7010615","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:31:10Z","timestamp":1690849870000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010615\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010615","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}