{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T21:11:21Z","timestamp":1779311481567,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":16,"publisher":"ACM","license":[{"start":{"date-parts":[[2011,2,12]],"date-time":"2011-02-12T00:00:00Z","timestamp":1297468800000},"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":[[2011,2,12]]},"DOI":"10.1145\/1947940.1948001","type":"proceedings-article","created":{"date-parts":[[2011,3,4]],"date-time":"2011-03-04T08:14:52Z","timestamp":1299226492000},"page":"285-288","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Reduct based Q-learning"],"prefix":"10.1145","author":[{"given":"Punit","family":"Pandey","sequence":"first","affiliation":[{"name":"Jaypee University of Engineering & Technology, Guna, M.P, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deepshikha","family":"Pandey","sequence":"additional","affiliation":[{"name":"Jaypee University of Engineering & Technology, Guna, M.P, India"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2011,2,12]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/2167525.2167533"},{"key":"e_1_3_2_1_2_1","volume-title":"Alberta, Canada, 4--6","author":"Peters J. F.","year":"2005","unstructured":"J. F. Peters, C. Henry, S. Ramanna, Reinforcement learning with pattern-based rewards. in proceding of forth International IASTED Conference. Computational Intelligence (CI 2005) Calgary, Alberta, Canada, 4--6 July 2005, 267--272"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-32392-9_13"},{"key":"e_1_3_2_1_5_1","unstructured":"C. Watkins \"Learning from Delayed Rewards\" PhD thesis Cambridge University Cambridge England 1989"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLC.2010.38"},{"issue":"6","key":"e_1_3_2_1_7_1","volume":"8","author":"Pandey Punit","year":"2010","unstructured":"Punit Pandey, Deepshikha Pandey, Dr. Shishir Kumar, \"Reinforcement Learning by Comparing Immediate Reward\", International Journal of Computer Science and Information Security, Vol. 8, No. 6, September 2010","journal-title":"International Journal of Computer Science and Information Security"},{"issue":"4","key":"e_1_3_2_1_8_1","volume":"9","author":"Pandey P. K.","year":"2009","unstructured":"P. K. Pandey, D. Tiwari, \" Temperature variation on Rough Actor-Critic Algorithm\", Global Journal Computer Science and Technology, Vol 9, No 4 (2009), Pennsylvania Digital Library","journal-title":"Global Journal Computer Science and Technology"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622737.1622748"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_1_11_1","unstructured":"C. Gaskett Q-Learning for Robot Control. Ph.D. Thesis Supervisor: A. Zelinsky Department of Systems Engineering The Australian National University 2002."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceeding of the 1993 Connectionist Models Summer School, Erblaum Associates. Nj.","author":"Schwartz S.","year":"1993","unstructured":"Thrun. S. and Schwartz. A. (1993), Issues in using function approximation for reinforcement learning, in Proceeding of the 1993 Connectionist Models Summer School, Erblaum Associates. Nj."},{"key":"e_1_3_2_1_13_1","volume-title":"Reinforcement Learning Architectures","author":"Sutton Richard S.","unstructured":"Richard S. Sutton, Reinforcement Learning Architectures, GTE Laboratories Incorporated, Waltham, MA 02254."},{"key":"e_1_3_2_1_14_1","volume-title":"Dept. of Computer Science","author":"O'Neill Tom","unstructured":"Tom O'Neill, Leland Aldridge, Harry Glaser, Q-Learning and Collection Agents, Dept. of Computer Science, University of Rochester"},{"key":"e_1_3_2_1_15_1","unstructured":"Vanden Berghen Frank Q-Learning IRIDIA Universit Libre de Bruxelles"},{"key":"e_1_3_2_1_16_1","volume-title":"Intelligent Systems Laboratory","author":"Kusiak Andrew","unstructured":"Andrew Kusiak, Rough Set Theory, Intelligent Systems Laboratory, The University of Iowa."}],"event":{"name":"ICCCS '11: International Conference on Communication, Computing & Security","location":"Rourkela Odisha India","acronym":"ICCCS '11"},"container-title":["Proceedings of the 2011 International Conference on Communication, Computing & Security"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1947940.1948001","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1947940.1948001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T20:31:44Z","timestamp":1779309104000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1947940.1948001"}},"subtitle":["an introduction"],"short-title":[],"issued":{"date-parts":[[2011,2,12]]},"references-count":16,"alternative-id":["10.1145\/1947940.1948001","10.1145\/1947940"],"URL":"https:\/\/doi.org\/10.1145\/1947940.1948001","relation":{},"subject":[],"published":{"date-parts":[[2011,2,12]]},"assertion":[{"value":"2011-02-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}