{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T07:15:30Z","timestamp":1779174930781,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":15,"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\/1273496.1273531","type":"proceedings-article","created":{"date-parts":[[2008,10,7]],"date-time":"2008-10-07T13:06:52Z","timestamp":1223384812000},"page":"273-280","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":240,"title":["Combining online and offline knowledge in UCT"],"prefix":"10.1145","author":[{"given":"Sylvain","family":"Gelly","sequence":"first","affiliation":[{"name":"Univ. Paris Sud, INRIA, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Silver","sequence":"additional","affiliation":[{"name":"University of Alberta, Edmonton, Alberta"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2007,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"e_1_3_2_1_2_1","first-page":"84","article-title":"Experiments in parameter learning using temporal differences","volume":"21","author":"Baxter J.","year":"1998","unstructured":"Baxter , J. , Tridgell , A. , & Weaver , L. ( 1998 ). Experiments in parameter learning using temporal differences . International Computer Chess Association Journal , 21 , 84 -- 99 . Baxter, J., Tridgell, A., & Weaver, L. (1998). Experiments in parameter learning using temporal differences. International Computer Chess Association Journal, 21, 84--99.","journal-title":"International Computer Chess Association Journal"},{"key":"e_1_3_2_1_3_1","volume-title":"Monte-Carlo Go","author":"Bruegmann B.","year":"1993","unstructured":"Bruegmann , B. ( 1993 ). Monte-Carlo Go . http:\/\/www.cgl.ucsf.edu\/go\/Programs\/Gobble.html. Bruegmann, B. (1993). Monte-Carlo Go. http:\/\/www.cgl.ucsf.edu\/go\/Programs\/Gobble.html."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/647480.727958"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/1777826.1777833"},{"key":"e_1_3_2_1_6_1","volume-title":"10th Advances in Computer Games Conference (pp. 97--108)","author":"Enzenberger M.","year":"2003","unstructured":"Enzenberger , M. ( 2003 ). Evaluation in Go by a neural network using soft segmentation . 10th Advances in Computer Games Conference (pp. 97--108) . Enzenberger, M. (2003). Evaluation in Go by a neural network using soft segmentation. 10th Advances in Computer Games Conference (pp. 97--108)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"e_1_3_2_1_9_1","volume-title":"17th International Joint Conference on Artificial Intelligence (pp. 529--534)","author":"Schaeffer J.","year":"2001","unstructured":"Schaeffer , J. , Hlynka , M. , & Jussila , V. ( 2001 ). Temporal difference learning applied to a high-performance game-playing program . 17th International Joint Conference on Artificial Intelligence (pp. 529--534) . Schaeffer, J., Hlynka, M., & Jussila, V. (2001). Temporal difference learning applied to a high-performance game-playing program. 17th International Joint Conference on Artificial Intelligence (pp. 529--534)."},{"key":"e_1_3_2_1_10_1","volume-title":"Temporal difference learning of position evaluation in the game of Go. Advances in Neural Information Processing Systems 6 (pp. 817--824)","author":"Schraudolph N.","year":"1994","unstructured":"Schraudolph , N. , Dayan , P. , & Sejnowski , T. ( 1994 ). Temporal difference learning of position evaluation in the game of Go. Advances in Neural Information Processing Systems 6 (pp. 817--824) . San Francisco : Morgan Kaufmann . Schraudolph, N., Dayan, P., & Sejnowski, T. (1994). Temporal difference learning of position evaluation in the game of Go. Advances in Neural Information Processing Systems 6 (pp. 817--824). San Francisco: Morgan Kaufmann."},{"key":"e_1_3_2_1_11_1","volume-title":"20th International Joint Conference on Artificial Intelligence (pp. 1053--1058)","author":"Silver D.","year":"2007","unstructured":"Silver , D. , Sutton , R. , & Mü \u00fcller , M. ( 2007 ). Reinforcement learning of local shape in the game of Go . 20th International Joint Conference on Artificial Intelligence (pp. 1053--1058) . Silver, D., Sutton, R., & Mü\u00fcller, M. (2007). Reinforcement learning of local shape in the game of Go. 20th International Joint Conference on Artificial Intelligence (pp. 1053--1058)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022633531479"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/101883.102055"},{"key":"e_1_3_2_1_14_1","volume-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding. Advances in Neural Information Processing Systems 8 (pp. 1038--1044)","author":"Sutton R.","year":"1996","unstructured":"Sutton , R. ( 1996 ). Generalization in reinforcement learning: Successful examples using sparse coarse coding. Advances in Neural Information Processing Systems 8 (pp. 1038--1044) . Sutton, R. (1996). Generalization in reinforcement learning: Successful examples using sparse coarse coding. Advances in Neural Information Processing Systems 8 (pp. 1038--1044)."},{"key":"e_1_3_2_1_15_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton R.","year":"1998","unstructured":"Sutton , R. , & Barto , A. ( 1998 ). Reinforcement learning: An introduction . Cambridge, MA : MIT Press . Sutton, R., & Barto, A. (1998). Reinforcement learning: An introduction. Cambridge, MA: MIT Press."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2007.368095"}],"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\/1273496.1273531","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1273496.1273531","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\/1273496.1273531"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,6,20]]},"references-count":15,"alternative-id":["10.1145\/1273496.1273531","10.1145\/1273496"],"URL":"https:\/\/doi.org\/10.1145\/1273496.1273531","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"}}]}}