{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:26:43Z","timestamp":1730194003653,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,3]]},"DOI":"10.1109\/adprl.2009.4927534","type":"proceedings-article","created":{"date-parts":[[2009,5,19]],"date-time":"2009-05-19T19:50:44Z","timestamp":1242762644000},"page":"117-123","source":"Crossref","is-referenced-by-count":4,"title":["Inferring bounds on the performance of a control policy from a sample of trajectories"],"prefix":"10.1109","author":[{"given":"Raphael","family":"Fonteneau","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Susan","family":"Murphy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Louis","family":"Wehenkel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Damien","family":"Ernst","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"263","reference":[{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"13"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1054010"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114725"},{"journal-title":"Model Predictive Control","year":"2004","author":"camacho","key":"3"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"2"},{"key":"1","volume":"3","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2022"},{"key":"7","first-page":"996","article-title":"finite-sample convergence rates for qlearning and indirect algorithms","volume":"12","author":"kearns","year":"1999","journal-title":"In Neural Information Processing Systems"},{"journal-title":"Theory of Financial Decision Making","year":"1987","author":"ingersoll","key":"6"},{"key":"5","article-title":"tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"4","first-page":"6","article-title":"selecting concise sets of samples for a reinforcement learning agent","author":"ernst","year":"2005","journal-title":"Proceedings of the third International Conference on Computational Intelligence Robotics and Autonomous Systems (CIRAS 2005)"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9868.00389"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1162\/jmlr.2003.4.6.1107"}],"event":{"name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","start":{"date-parts":[[2009,3,30]]},"location":"Nashville, TN, USA","end":{"date-parts":[[2009,4,2]]}},"container-title":["2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4910084\/4927513\/04927534.pdf?arnumber=4927534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,17]],"date-time":"2017-03-17T20:28:09Z","timestamp":1489782489000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4927534\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,3]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/adprl.2009.4927534","relation":{},"subject":[],"published":{"date-parts":[[2009,3]]}}}