{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T06:12:18Z","timestamp":1785823938306,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2009,6,14]],"date-time":"2009-06-14T00:00:00Z","timestamp":1244937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2009,6,14]]},"DOI":"10.1145\/1553374.1553501","type":"proceedings-article","created":{"date-parts":[[2009,6,16]],"date-time":"2009-06-16T09:34:36Z","timestamp":1245144876000},"page":"993-1000","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":223,"title":["Fast gradient-descent methods for temporal-difference learning with linear function approximation"],"prefix":"10.1145","author":[{"given":"Richard S.","family":"Sutton","sequence":"first","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamid Reza","family":"Maei","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Doina","family":"Precup","sequence":"additional","affiliation":[{"name":"McGill University, Montreal, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shalabh","family":"Bhatnagar","sequence":"additional","affiliation":[{"name":"Indian Institute of Science, Bangalore, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Silver","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Csaba","family":"Szepesv\u00e1ri","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Wiewiora","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2009,6,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-007-5038-2"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"e_1_3_2_1_3_1","unstructured":"Baird L. C. (1999). Reinforcement Learning Through Gradient Descent. PhD thesis Carnegie-Mellon University."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/21.229449"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6911(97)90015-3"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992701"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/1597538.1597596"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90018-X"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/645530.655817"},{"key":"e_1_3_2_1_13_1","volume-title":"Off-policy learning with recognizers. Advances in Neural Information Processing Systems 18","author":"Precup D.","year":"2006","unstructured":"Precup, D., Sutton, R. S., Paduraru, C., Koop, A., Singh, S. (2006). Off-policy learning with recognizers. Advances in Neural Information Processing Systems 18."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/1625275.1625446"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/1777826.1777837"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"e_1_3_2_1_18_1","volume-title":"A convergent O(n) algorithm for off-policy temporal-difference learning with linear function approximation. Advances in Neural Information Processing Systems 21","author":"Sutton R. S.","year":"2009","unstructured":"Sutton, R. S., Szepesv\u00e1ri, Cs., Maei, H. R. (2009). A convergent O(n) algorithm for off-policy temporal-difference learning with linear function approximation. Advances in Neural Information Processing Systems 21."}],"event":{"name":"ICML '09: The 26th Annual International Conference on Machine Learning held in conjunction with the 2007 International Conference on Inductive Logic Programming","location":"Montreal Quebec Canada","acronym":"ICML '09","sponsor":["MITACS","Microsoft Research Microsoft Research","NSF"]},"container-title":["Proceedings of the 26th Annual International Conference on Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1553374.1553501","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1553374.1553501","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,17]],"date-time":"2026-05-17T19:54:19Z","timestamp":1779047659000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1553374.1553501"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,6,14]]},"references-count":18,"alternative-id":["10.1145\/1553374.1553501","10.1145\/1553374"],"URL":"https:\/\/doi.org\/10.1145\/1553374.1553501","relation":{},"subject":[],"published":{"date-parts":[[2009,6,14]]},"assertion":[{"value":"2009-06-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}