{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T03:49:27Z","timestamp":1763178567804},"reference-count":29,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,5]]},"DOI":"10.1109\/robot.2009.5152840","type":"proceedings-article","created":{"date-parts":[[2009,8,24]],"date-time":"2009-08-24T11:04:04Z","timestamp":1251111844000},"page":"2525-2532","source":"Crossref","is-referenced-by-count":10,"title":["Constructing action set from basis functions for reinforcement learning of robot control"],"prefix":"10.1109","author":[{"given":"Akihiko","family":"Yamaguchi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Jun Takamatsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Tsukasa Ogasawara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50045-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(98)00054-2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015853"},{"key":"ref13","article-title":"Reinforcement learning with high-dimensional, continuous actions","author":"baird","year":"1993","journal-title":"Tech Rep WL-TR-93-1147"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1098-111X(199802\/03)13:2\/3<257::AID-INT9>3.0.CO;2-Z"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2003.11.004"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.7210\/jrsj.27.209"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"ref17"},{"key":"ref18","article-title":"On-line Q-learning using connectionist systems","author":"rummery","year":"1994","journal-title":"Technical Report CUED\/F-INFENG\/TR291"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114724"},{"journal-title":"Automated discovery of options in reinforcement learning","year":"2004","author":"stolle","key":"ref28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363871"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-36755-1_25"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2001.980135"},{"key":"ref6","article-title":"Reinforcement learning for a vision based mobile robot","author":"gaskett","year":"2000","journal-title":"the IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS'00)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MFI.1999.815999"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2003.11.006"},{"key":"ref8","first-page":"287","article-title":"Competitive-cooperative-concurrent reinforcement learning with importance sampling","author":"uchibe","year":"2004","journal-title":"Proc of International Conference on Simulation of Adaptive Behavior From Animals and Animats"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2004.03.006"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.1998.724846"},{"key":"ref9","first-page":"2937","article-title":"Multi-layered learning systems for vision-based behavior acquisition of a real mobile robot","author":"takahashi","year":"2003","journal-title":"SICE 2003 Annual Conference"},{"key":"ref1","article-title":"Dyna-style planning with linear function approximation and prioritized sweeping","author":"sutton","year":"2008","journal-title":"Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50035-0"},{"key":"ref21","first-page":"152","article-title":"Reinforcement learning in pomdps with function approximation","author":"kimura","year":"1997","journal-title":"ICML '97 Proceedings of the Fourteenth International Conference on Machine Learning"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(98)00066-5"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"ref26","first-page":"361","article-title":"Automatic discovery of subgoals in reinforcement learning using diverse density","author":"mcgovern","year":"2001","journal-title":"Proceedings of the Eighteenth International Conference on Machine Learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"}],"event":{"name":"2009 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2009,5,12]]},"location":"Kobe","end":{"date-parts":[[2009,5,17]]}},"container-title":["2009 IEEE International Conference on Robotics and Automation"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5076472\/5152175\/05152840.pdf?arnumber=5152840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,17]],"date-time":"2017-03-17T13:11:44Z","timestamp":1489756304000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5152840\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,5]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/robot.2009.5152840","relation":{},"subject":[],"published":{"date-parts":[[2009,5]]}}}