{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T15:51:38Z","timestamp":1729612298234,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,10]]},"DOI":"10.1109\/icumt.2010.5676598","type":"proceedings-article","created":{"date-parts":[[2011,1,3]],"date-time":"2011-01-03T15:50:24Z","timestamp":1294069824000},"page":"450-457","source":"Crossref","is-referenced-by-count":4,"title":["Statistically linearized least-squares temporal differences"],"prefix":"10.1109","author":[{"given":"Matthieu","family":"Geist","sequence":"first","affiliation":[]},{"given":"Olivier","family":"Pietquin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICUMT.2010.5676597"},{"key":"ref11","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1023\/A:1022192903948","article-title":"Least Squares Policy Evaluation Algorithms with Linear Function Approximation","volume":"13","author":"nedi?","year":"2003","journal-title":"Discrete Event Dynamic Systems Theory and Applications"},{"key":"ref12","first-page":"1107","article-title":"Least-Squares Policy Iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"Reinforcement Learning for Humanoid Robotics","author":"peters","year":"2003","journal-title":"Third IEEE-RAS International Conference on Humanoid Robots (Humanoids 2003)"},{"journal-title":"An Introduction to Multivariate Statistical Analysis","year":"1984","author":"anderson","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2003.823141"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(00)00089-3"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2010.5589236"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1974-0343558-6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"ref4","first-page":"1204","article-title":"Convergent Temporal-Difference Learning with Arbitrary Smooth Function Approximation","volume":"22","author":"maei","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-006-8134-8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927543"},{"key":"ref7","first-page":"154","article-title":"Bayes Meets Bellman: The Gaussian Process Approach to Temporal Difference Learning","author":"engel","year":"2003","journal-title":"Proc of the International Conference on Machine Learning (ICML)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"journal-title":"Reinforcement Learning An Introduction (Adaptive Computation and Machine Learning)","year":"1998","author":"sutton","key":"ref1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102377"},{"key":"ref20","first-page":"317","article-title":"Neural Fitted Q Iteration – First Experiences with a Data Efficient Neural Reinforcement Learning Method","author":"riedmiller","year":"2005","journal-title":"European Conference on Machine Learning"}],"event":{"name":"2010 International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT 2010)","start":{"date-parts":[[2010,10,18]]},"location":"Moscow, Russia","end":{"date-parts":[[2010,10,20]]}},"container-title":["International Congress on Ultra Modern Telecommunications and Control Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5655222\/5676472\/05676598.pdf?arnumber=5676598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,19]],"date-time":"2017-06-19T13:57:40Z","timestamp":1497880660000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5676598\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,10]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icumt.2010.5676598","relation":{},"subject":[],"published":{"date-parts":[[2010,10]]}}}