{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T11:49:58Z","timestamp":1789904998808,"version":"4.0.1"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/iros.2003.1250667","type":"proceedings-article","created":{"date-parts":[[2004,7,8]],"date-time":"2004-07-08T20:05:44Z","timestamp":1089317144000},"page":"430-435","source":"Crossref","is-referenced-by-count":20,"title":["A robot that reinforcement-leams to identify and memorize important previous observations"],"prefix":"10.1109","volume":"1","author":[{"given":"B.","family":"Bakker","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"V.","family":"Zhumatiy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G.","family":"Gruener","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J.","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref3","article-title":"Multi-player residual advantage learning with general function approximation","author":"harmon","year":"1996","journal-title":"Wright Patterson Air Force Base"},{"key":"ref10","article-title":"Learning to use selective attention and short-term memory in sequential tasks","author":"mccallum","year":"1996","journal-title":"Proc Int Conf on the Simulation of Adaptive Behavior"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1023\/A:1009645229062"},{"key":"ref5","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":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref8","article-title":"Mobile robot learning of delayed response tasks through event extraction: A solution to the road sign problem and beyond","author":"lin\u00e5ker","year":"2001","journal-title":"Proc IJCAI'2001"},{"key":"ref7","article-title":"Reinforcement learning with hidden states","author":"lin","year":"1993","journal-title":"Proc of the 2nd Int Conf on Simulation of Adaptive Behavior"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IRDS.2002.1041511"},{"key":"ref9","article-title":"An optimization-based categorization of reinforcement learning environments","author":"littman","year":"1993","journal-title":"Proc of the 2nd Int Conf on Simulation of Adaptive Behavior"},{"key":"ref1","article-title":"Reinforcement learning with Long Short-Term Memory","author":"bakker","year":"2002","journal-title":"NIPS 14"}],"event":{"name":"2003 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2003) (Cat. No.03CH37453)","location":"Las Vegas, Nevada, USA","acronym":"IROS-03"},"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\/01250667.pdf?arnumber=1250667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,2]],"date-time":"2020-04-02T17:41:00Z","timestamp":1585849260000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1250667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/iros.2003.1250667","relation":{},"subject":[]}}