{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T05:19:30Z","timestamp":1722921570858},"reference-count":19,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/ijcnn.2004.1380884","type":"proceedings-article","created":{"date-parts":[[2005,1,31]],"date-time":"2005-01-31T12:28:44Z","timestamp":1107174524000},"page":"1817-1822","source":"Crossref","is-referenced-by-count":0,"title":["A solving method for MDPs by minimizing variational free energy"],"prefix":"10.1109","volume":"3","author":[{"given":"J.","family":"Yoshimoto","sequence":"first","affiliation":[]},{"given":"S.","family":"Ishii","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","first-page":"514","article-title":"Gaussian processes for regression","author":"williams","year":"1996","journal-title":"Advances in Neural Information Processing Systems 8"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(02)00056-4"},{"journal-title":"Algorithms for Linear-Quadratic Optimization","year":"1996","author":"sima","key":"18"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016674"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1023\/A:1020281327116"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1963.1105600"},{"key":"11","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Advances in Neural Information Processing Systems 12"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299731669X"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"3"},{"journal-title":"Dynamic Programming and Markov Processes","year":"1960","author":"howard","key":"2"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50044-X"},{"journal-title":"Dynamic Programming","year":"1957","author":"bellman","key":"1"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015961"},{"key":"5","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","author":"sutton","year":"1996","journal-title":"Advances in Neural Information Processing Systems 8"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"4"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"}],"event":{"name":"2004 IEEE International Joint Conference on Neural Networks","acronym":"IJCNN-04","location":"Budapest, Hungary"},"container-title":["2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/9486\/30107\/01380884.pdf?arnumber=1380884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,14]],"date-time":"2017-03-14T21:01:46Z","timestamp":1489525306000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1380884\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2004.1380884","relation":{},"subject":[]}}