{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T07:49:51Z","timestamp":1729669791364,"version":"3.28.0"},"reference-count":9,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/ijcnn.2003.1224032","type":"proceedings-article","created":{"date-parts":[[2004,6,22]],"date-time":"2004-06-22T16:27:43Z","timestamp":1087921663000},"page":"2905-2909","source":"Crossref","is-referenced-by-count":0,"title":["An enhanced least-squares approach for reinforcement learning"],"prefix":"10.1109","volume":"4","author":[{"family":"Hailin Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C.H.","family":"Dagh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018056104778"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement Learning: a survey","volume":"4","author":"kadbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref6","article-title":"Model free Least Squares policy iteration","author":"lagoudakis","year":"2001","journal-title":"Proceedings of the 14th Neural Information Processing Systems (NIPS-14)"},{"key":"ref5","first-page":"326","article-title":"Policy iteration for factored MDPs","author":"koller","year":"2000","journal-title":"Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence (UAI-00) Morgan Kaufmann"},{"key":"ref8","first-page":"511","article-title":"Algorithm selection using Reinforcement Learning","author":"lagoudakis","year":"2000","journal-title":"Proceedings of the 7th International Conference on Mach nc Learning"},{"key":"ref7","first-page":"2513","article-title":"Orthogonal Least Squares algorithm for Radial Basis Function Networks","volume":"21","author":"chen","year":"1990","journal-title":"IEEE Transactions on Neural Networks"},{"article-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref2"},{"article-title":"Temporal aspects of credit assignment in Reinforcement Learning","year":"1984","author":"sutton","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"}],"event":{"name":"International Joint Conference on Neural Networks, 2003.","acronym":"IJCNN-03","location":"Portland, Oregon USA"},"container-title":["Proceedings of the International Joint Conference on Neural Networks, 2003."],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8672\/27487\/01224032.pdf?arnumber=1224032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,2]],"date-time":"2020-04-02T10:11:31Z","timestamp":1585822291000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1224032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":9,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2003.1224032","relation":{},"subject":[]}}