{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T06:36:28Z","timestamp":1730270188082,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/iros.2003.1250668","type":"proceedings-article","created":{"date-parts":[[2004,7,8]],"date-time":"2004-07-08T20:05:44Z","timestamp":1089317144000},"page":"436-441","source":"Crossref","is-referenced-by-count":1,"title":["A reinforcement learning approach involving a shortest path finding algorithm"],"prefix":"10.1109","volume":"1","author":[{"family":"Woo Young Kwon","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Sangboon Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Il Hong Suh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/105971239700500302"},{"journal-title":"Reinforcement Learning","year":"1997","author":"sutton","key":"ref11"},{"key":"ref12","first-page":"237","article-title":"Reinforcement Learning: A Survey","volume":"4","author":"kaelbling","year":"0","journal-title":"J Artiftciallntelligence Research"},{"article-title":"Reinforcement Learning with selective Perception and Hidden State","year":"1996","author":"mccallum","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/3477.846230"},{"article-title":"Algorithm for Sequential Decision Making","year":"1996","author":"littman","key":"ref15"},{"key":"ref16","article-title":"Reinforcement learning in non-Markov environments","author":"whitehead","year":"1993","journal-title":"Artificial Intelligence"},{"journal-title":"Foundation of Algorithms Using C++ Pseudocode","year":"1998","author":"neapolitan","key":"ref17"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7091-3671-3"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JRPROC.1961.287775"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.101.2616.160"},{"journal-title":"An Introduction to Theories of Learning","year":"2001","author":"hergenhahn","key":"ref5"},{"journal-title":"Reinforcement Learning","year":"1997","author":"sutton","key":"ref8"},{"key":"ref7","article-title":"Biological Learning and Artificial Intelligence","author":"balkenius","year":"1996","journal-title":"University of Rochester"},{"journal-title":"The Behavior of Organisms","year":"1938","author":"skinner","key":"ref2"},{"journal-title":"Conditioned Reflexes","year":"1927","author":"pavolov","key":"ref1"},{"article-title":"Learning from Delayed Rewards","year":"1989","author":"watkins","key":"ref9"}],"event":{"name":"2003 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)","acronym":"IROS-03","location":"Las Vegas, Nevada, USA"},"container-title":["Proceedings 2003 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8832\/27983\/01250668.pdf?arnumber=1250668","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,14]],"date-time":"2017-03-14T17:52:44Z","timestamp":1489513964000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1250668\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/iros.2003.1250668","relation":{},"subject":[]}}