{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,2]],"date-time":"2025-04-02T05:43:35Z","timestamp":1743572615078,"version":"3.28.0"},"reference-count":11,"publisher":"IEEE Comput. Soc","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/iat.2003.1241115","type":"proceedings-article","created":{"date-parts":[[2004,3,2]],"date-time":"2004-03-02T02:26:50Z","timestamp":1078194410000},"page":"432-437","source":"Crossref","is-referenced-by-count":1,"title":["Q-learning automaton"],"prefix":"10.1109","author":[{"family":"Fei Qian","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Hironori Hirata","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-83069-3"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref3"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1985.6313371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-247-2.50017-6"},{"key":"ref5","article-title":"Toward a Theory of Reinforcement Learning Connectionist Systems","author":"willianms","year":"1988","journal-title":"Technical Report NU-CCS-88–3"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1007\/3-540-62934-3_39","article-title":"A Modular Approach to Multi-agent Reinforcement Learning","author":"ono","year":"1997","journal-title":"Distributed Artificial Intelligence Meets Machine Learning"},{"key":"ref7","article-title":"Adaptive Neural Networks for Learning Control: Some Computational Experiments","volume":"170","author":"barto","year":"1986","journal-title":"Proc of the IEEE Workshop on Intelligent Control"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement Learning: A Survey","volume":"4","author":"kaelbking","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref9","article-title":"Automatic Programming of Behavior-based Robots using Reinforcement Learning","volume":"774","author":"mahadevan","year":"1991","journal-title":"Proc 9th Nat Conf on Artificial Intelligence"},{"journal-title":"Learning Automata-An Introduction Prentice-Hall International","year":"1989","author":"narendra","key":"ref1"}],"event":{"name":"2003 IEEE\/WIC International Conference on Intelligent Agent Technology","acronym":"IAT-03","location":"Halifax, NS, Canada"},"container-title":["IEEE\/WIC International Conference on Intelligent Agent Technology, 2003. IAT 2003."],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8789\/27820\/01241115.pdf?arnumber=1241115","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,3,31]],"date-time":"2020-03-31T08:57:58Z","timestamp":1585645078000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1241115\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/iat.2003.1241115","relation":{},"subject":[]}}