{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T16:35:52Z","timestamp":1729614952648,"version":"3.28.0"},"reference-count":6,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/icsmc.2004.1401152","type":"proceedings-article","created":{"date-parts":[[2005,3,31]],"date-time":"2005-03-31T13:26:51Z","timestamp":1112275611000},"page":"5980-5984","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement learning based on spatial and temporal association of states"],"prefix":"10.1109","volume":"6","author":[{"family":"Xiao-Dong Zhuang","sequence":"first","affiliation":[]},{"family":"Qing-Chun Meng","sequence":"additional","affiliation":[]},{"family":"Bo Yin","sequence":"additional","affiliation":[]},{"family":"Yun Gao","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"3","article-title":"Direct gradient-based reinforcement learning: I. gradient estimation algorithms","author":"baxter","year":"1999","journal-title":"Technical Report"},{"key":"2","first-page":"539","article-title":"Learning and sequential decision making","author":"barto","year":"1990","journal-title":"Learning and Computational Neuroscience"},{"key":"1","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"6","first-page":"136","article-title":"Relational reinforcement learning","author":"dzeroski","year":"1998","journal-title":"Proceedings of the Fifteenth International Conference on Machine Learning"},{"key":"5","first-page":"271","article-title":"Feudal reinforcement learning","volume":"5","author":"dayan","year":"1993","journal-title":"Advances in neural information processing systems"},{"key":"4","first-page":"769","article-title":"Tree based discretization for continuous state space reinforcement learning","author":"uther","year":"1998","journal-title":"Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI-98)"}],"event":{"name":"2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)","acronym":"ICSMC-04","location":"The Hague, Netherlands"},"container-title":["2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9622\/30425\/01401152.pdf?arnumber=1401152","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,2,8]],"date-time":"2019-02-08T00:06:19Z","timestamp":1549584379000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1401152\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":6,"URL":"https:\/\/doi.org\/10.1109\/icsmc.2004.1401152","relation":{},"subject":[]}}