{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T20:48:53Z","timestamp":1774385333397,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2007,5,14]],"date-time":"2007-05-14T00:00:00Z","timestamp":1179100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000145","name":"Division of Information and Intelligent Systems","doi-asserted-by":"publisher","award":["IIS-0237699"],"award-info":[{"award-number":["IIS-0237699"]}],"id":[{"id":"10.13039\/100000145","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-04-1-0035"],"award-info":[{"award-number":["HR0011-04-1-0035"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["EIA-0303609"],"award-info":[{"award-number":["EIA-0303609"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-04-1-0545"],"award-info":[{"award-number":["N00014-04-1-0545"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2007,5,14]]},"DOI":"10.1145\/1329125.1329351","type":"proceedings-article","created":{"date-parts":[[2008,1,18]],"date-time":"2008-01-18T15:04:38Z","timestamp":1200668678000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["IFSA"],"prefix":"10.1145","author":[{"given":"Mazda","family":"Ahmadi","sequence":"first","affiliation":[{"name":"The University of Texas at Austin, Austin, Texas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew E.","family":"Taylor","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, Texas"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Stone","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, Texas"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2007,5,14]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.5555\/340534.340892"},{"key":"e_1_3_2_1_2_1","first-page":"1017","volume-title":"Advances in Neural Information Processing Systems 8","author":"Crites R. H.","year":"1996","unstructured":"R. H. Crites and A. G. Barto. Improving elevator performance using reinforcement learning. In D. S. Touretzky, M. C. Mozer, and M. E. Hasselmo, editors, Advances in Neural Information Processing Systems 8, pages 1017--1023, Cambridge, MA, 1996. MIT Press."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the Fifteenth International Conference on Machine Learning. Morgan Kaufmann","author":"Dietterich T. G.","year":"1998","unstructured":"T. G. Dietterich. The MAXQ method for hierarchical reinforcement learning. In Proceedings of the Fifteenth International Conference on Machine Learning. Morgan Kaufmann, 1998."},{"key":"e_1_3_2_1_4_1","volume-title":"Reinforcement Learning Benchmarks and Bake-offs II A workshop at the 2005 NIPS conference","author":"Edmunds T.","year":"2005","unstructured":"T. Edmunds. An optimum agent for the discrete triathlon. In Reinforcement Learning Benchmarks and Bake-offs II A workshop at the 2005 NIPS conference, 2005."},{"key":"e_1_3_2_1_5_1","first-page":"243","volume-title":"Proc. 19th International Conf. on Machine Learning","author":"Hengst B.","year":"2002","unstructured":"B. Hengst. Discovering hierarchy in reinforcement learning with HEXQ. In Proc. 19th International Conf. on Machine Learning, pages 243--250, 2002."},{"key":"e_1_3_2_1_6_1","volume-title":"The AAAI-2004 Workshop on Supervisory Control of Learning and Adaptive Systems","author":"Kuhlmann G.","year":"2004","unstructured":"G. Kuhlmann, P. Stone, R. Mooney, and J. Shavlik. Guiding a reinforcement learner with natural language advice: Initial results in RoboCup soccer. In The AAAI-2004 Workshop on Supervisory Control of Learning and Adaptive Systems, July 2004."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/945365.964290"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114730"},{"key":"e_1_3_2_1_9_1","volume-title":"Advances in Neural Information Processing Systems 17","author":"Ng A. Y.","year":"2004","unstructured":"A. Y. Ng, H. J. Kim, M. I. Jordan, and S. Sastry. Autonomous helicopter flight via reinforcement learning. In Advances in Neural Information Processing Systems 17. MIT Press, 2004. To Appear."},{"key":"e_1_3_2_1_10_1","unstructured":"G. A. Rummery and M. Niranjan. On-line Q-learning using connectionist systems. Technical Report CUED\/F-INFENG-RT 116 Engineering Department Cambridge University 1994."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/518662"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/646586.696867"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1177\/105971230501300301"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/551283"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"}],"event":{"name":"AAMAS07: International Conference on Autonomous Agents and Mulitagent Systems","location":"Honolulu Hawaii","acronym":"AAMAS07","sponsor":["IFAAMAS"]},"container-title":["Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1329125.1329351","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/1329125.1329351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T17:21:49Z","timestamp":1774372909000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/1329125.1329351"}},"subtitle":["incremental feature-set augmentation for reinforcement learning tasks"],"short-title":[],"issued":{"date-parts":[[2007,5,14]]},"references-count":17,"alternative-id":["10.1145\/1329125.1329351","10.1145\/1329125"],"URL":"https:\/\/doi.org\/10.1145\/1329125.1329351","relation":{},"subject":[],"published":{"date-parts":[[2007,5,14]]},"assertion":[{"value":"2007-05-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}