{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T01:54:15Z","timestamp":1729648455926,"version":"3.28.0"},"reference-count":13,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007,10]]},"DOI":"10.1109\/iros.2007.4399401","type":"proceedings-article","created":{"date-parts":[[2008,1,9]],"date-time":"2008-01-09T19:23:35Z","timestamp":1199906615000},"page":"88-95","source":"Crossref","is-referenced-by-count":11,"title":["Reinforcement learning in multi-dimensional state-action space using random rectangular coarse coding and Gibbs sampling"],"prefix":"10.1109","author":[{"given":"Hajime","family":"Kimura","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1038","article-title":"Generalization in reinforcement learning: Successful examples using sparse coarse coding","volume":"8","author":"sutton","year":"1996","journal-title":"Advances in neural information processing systems"},{"year":"1998","author":"sutton","journal-title":"Reinforcement Learning An Introduction A Bradford Book","key":"ref11"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1109\/MFI.1999.815999"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/BF00992698"},{"key":"ref4","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"},{"year":"1999","author":"jordan","journal-title":"Learning in Graphical Models","key":"ref3"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1007\/BF00993591"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1016\/B978-1-55860-307-3.50030-7"},{"key":"ref8","first-page":"1063","article-title":"Reinforcement learning with factored states and actions","volume":"5","author":"sallans","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1023\/A:1017988514716","volume":"49","author":"millan","year":"2002","journal-title":"Continuous-Action Q-Learning Machine Learning"},{"key":"ref2","first-page":"243","author":"hengst","year":"0","journal-title":"Discovering Hierarchy in Reinforcement Learning with HEXQ Proc of 19th International Conference on Machine Learning (ICML2002)"},{"year":"1996","author":"bertsekas","journal-title":"Neuro-Dynamic Programming","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1177\/105971239700600201"}],"event":{"name":"2007 IEEE\/RSJ International Conference on Intelligent Robots and Systems","start":{"date-parts":[[2007,10,29]]},"location":"San Diego, CA, USA","end":{"date-parts":[[2007,11,2]]}},"container-title":["2007 IEEE\/RSJ International Conference on Intelligent Robots and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4398943\/4398944\/04399401.pdf?arnumber=4399401","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T04:10:50Z","timestamp":1708488650000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4399401\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,10]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/iros.2007.4399401","relation":{},"subject":[],"published":{"date-parts":[[2007,10]]}}}