{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T00:21:36Z","timestamp":1778372496864,"version":"3.51.4"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,3]]},"DOI":"10.1109\/adprl.2009.4927542","type":"proceedings-article","created":{"date-parts":[[2009,5,19]],"date-time":"2009-05-19T19:50:44Z","timestamp":1242762644000},"page":"177-184","source":"Crossref","is-referenced-by-count":100,"title":["A theoretical and empirical analysis of Expected Sarsa"],"prefix":"10.1109","author":[{"given":"Harm","family":"van Seijen","sequence":"first","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Hado","family":"van Hasselt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Shimon","family":"Whiteson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]},{"given":"Marco","family":"Wiering","sequence":"additional","affiliation":[],"role":[{"role":"author","vocab":"crossref"}]}],"member":"263","reference":[{"key":"3","first-page":"679","article-title":"a markov decision process","volume":"6","author":"bellman","year":"1957","journal-title":"Journal of Methematical Mechanics"},{"key":"2","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"10","volume":"166","author":"rummery","year":"1994","journal-title":"On-line Q-learning using connectionist systems"},{"key":"1","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"reinforcement learning: a survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"7","first-page":"369","article-title":"generalization in reinforcement learning: safely approximating the value function","volume":"7","author":"boyan","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"4","author":"bellman","year":"1957","journal-title":"Dynamic Programming"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50040-2"},{"key":"11","first-page":"1038","article-title":"generalization in reinforcement learning: successful examples using sparse coarse coding","volume":"8","author":"sutton","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007678930559"}],"event":{"name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","location":"Nashville, TN, USA","start":{"date-parts":[[2009,3,30]]},"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\/04927542.pdf?arnumber=4927542","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T06:51:30Z","timestamp":1558335090000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4927542\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,3]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/adprl.2009.4927542","relation":{},"subject":[],"published":{"date-parts":[[2009,3]]}}}