{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,4]],"date-time":"2026-10-04T01:20:53Z","timestamp":1791076853452,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2007,6,20]],"date-time":"2007-06-20T00:00:00Z","timestamp":1182297600000},"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":[[2007,6,20]]},"DOI":"10.1145\/1273496.1273591","type":"proceedings-article","created":{"date-parts":[[2008,10,7]],"date-time":"2008-10-07T13:06:52Z","timestamp":1223384812000},"page":"751-758","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Tracking value function dynamics to improve reinforcement learning with piecewise linear function approximation"],"prefix":"10.1145","author":[{"given":"Chee Wee","family":"Phua","sequence":"first","affiliation":[{"name":"University of New South Wales, Sydney NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Fitch","sequence":"additional","affiliation":[{"name":"University of New South Wales, Sydney NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2007,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017936530646"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114723"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-006-8134-8"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622262.1622268"},{"key":"e_1_3_2_1_6_1","first-page":"356","volume-title":"Twenty-First National Conference on Artificial Intelligence (AAAI-06)","author":"Geramifard A.","year":"2006","unstructured":"Geramifard , A. , Bowling , M. , & Sutton , R. S. ( 2006 ). Incremental least-squares temporal difference learning . Twenty-First National Conference on Artificial Intelligence (AAAI-06) (pp. 356 -- 361 ). Geramifard, A., Bowling, M., & Sutton, R. S. (2006). Incremental least-squares temporal difference learning. Twenty-First National Conference on Artificial Intelligence (AAAI-06) (pp. 356--361)."},{"key":"e_1_3_2_1_7_1","volume-title":"Adaptive filter theory","author":"Haykin S.","year":"2001","unstructured":"Haykin , S. ( 2001 ). Adaptive filter theory ( 4 th edition). Prentice Hall . Haykin, S. (2001). Adaptive filter theory (4th edition). Prentice Hall.","edition":"4"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/945365.964290"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017992615625"},{"key":"e_1_3_2_1_11_1","volume-title":"A convergent form of approximate policy iteration. Neural Information Processing Systems (pp. 1595--1602)","author":"Perkins T. J.","year":"2002","unstructured":"Perkins , T. J. , & Precup , D. ( 2002 ). A convergent form of approximate policy iteration. Neural Information Processing Systems (pp. 1595--1602) . Vancouver, British Columbia, Canada : MIT Press . Perkins, T. J., & Precup, D. (2002). A convergent form of approximate policy iteration. Neural Information Processing Systems (pp. 1595--1602). Vancouver, British Columbia, Canada: MIT Press."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-005-1121-8"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","DOI":"10.1002\/0470045345","volume-title":"Optimal state estimation: Kalman, H-infinity, and nonlinear approaches","author":"Simon D.","year":"2006","unstructured":"Simon , D. ( 2006 ). Optimal state estimation: Kalman, H-infinity, and nonlinear approaches . Wiley-Interscience . Simon, D. (2006). Optimal state estimation: Kalman, H-infinity, and nonlinear approaches. Wiley-Interscience."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01211647"},{"key":"e_1_3_2_1_15_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton R. S.","year":"1998","unstructured":"Sutton , R. S. , & Barto , A. G. ( 1998 ). Reinforcement learning: An introduction . Cambridge, MA : MIT Press . Sutton, R. S., & Barto, A. G. (1998). Reinforcement learning: An introduction. Cambridge, MA: MIT Press."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.21236\/AD0241531"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622407.1622414"}],"event":{"name":"ICML '07 & ILP '07: The 24th Annual International Conference on Machine Learning held in conjunction with the 2007 International Conference on Inductive Logic Programming","location":"Corvalis Oregon USA","acronym":"ICML '07 & ILP '07","sponsor":["Machine Learning Journal"]},"container-title":["Proceedings of the 24th international conference on Machine learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1273496.1273591","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1273496.1273591","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T14:58:01Z","timestamp":1750258681000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1273496.1273591"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,6,20]]},"references-count":18,"alternative-id":["10.1145\/1273496.1273591","10.1145\/1273496"],"URL":"https:\/\/doi.org\/10.1145\/1273496.1273591","relation":{},"subject":[],"published":{"date-parts":[[2007,6,20]]},"assertion":[{"value":"2007-06-20","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}