{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:27:03Z","timestamp":1730194023549,"version":"3.28.0"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,12]]},"DOI":"10.1109\/adprl.2014.7010611","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":0,"title":["Accelerated gradient temporal difference learning algorithms"],"prefix":"10.1109","author":[{"given":"Dominik","family":"Meyer","sequence":"first","affiliation":[]},{"given":"Remy","family":"Degenne","sequence":"additional","affiliation":[]},{"given":"Ahmed","family":"Omrane","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Shen","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","first-page":"809","article-title":"Policy Evaluation with Temporal Differences: A Survey and Comparison","volume":"15","author":"dann","year":"2014"},{"key":"ref3","first-page":"49","article-title":"Least-squares temporal difference learning","author":"boyan","year":"1999","journal-title":"Proceedings of the 16th International Conference on Machine Learning"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390227"},{"key":"ref10","first-page":"1609","article-title":"A convergent O(n) algorithm for off-policy temporal difference learning with linear function approximation","author":"sutton","year":"2008","journal-title":"Advances in Neural Information Processing Systems 21"},{"key":"ref5","first-page":"781","article-title":"Accelerated Gradient Methods for Stochastic Optimization and Online Learning","author":"hu","year":"2009","journal-title":"Advances in Neural Information Processing Systems 22"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref8","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","author":"sutskever","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref7","first-page":"372","article-title":"A method of solving a convex programming problem with convergence rate O(1\/k2)","volume":"27","author":"nesterov","year":"1983","journal-title":"Soviet Mathematics Doklady"},{"key":"ref2","first-page":"231","article-title":"Improved temporal difference methods with linear function approximation","author":"bertsekas","year":"2004","journal-title":"Learning and Approximate Dynamic Programming"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"}],"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\/07010611.pdf?arnumber=7010611","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,23]],"date-time":"2017-03-23T21:41:30Z","timestamp":1490305290000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7010611\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,12]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/adprl.2014.7010611","relation":{},"subject":[],"published":{"date-parts":[[2014,12]]}}}