{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:21:42Z","timestamp":1729624902888,"version":"3.28.0"},"reference-count":15,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/iros.1996.568991","type":"proceedings-article","created":{"date-parts":[[2002,12,24]],"date-time":"2002-12-24T11:50:07Z","timestamp":1040730607000},"page":"1345-1352","source":"Crossref","is-referenced-by-count":6,"title":["Reinforcement learning of sensor-based reaching strategies for a two-link manipulator"],"prefix":"10.1109","volume":"3","author":[{"given":"P.","family":"Martin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.","family":"del R. Millan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50021-9"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/0167-8191(90)90081-J"},{"key":"ref12","first-page":"309","article-title":"A modular Q-learning architecture for manipulator task decomposition","author":"tham","year":"1994","journal-title":"11th Int Conf on Machine Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1994.374662"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(92)90036-T"},{"journal-title":"Learning goal-directed obstacle-avoiding strategies through reinforcement for a two-link sensor-based manipulator","year":"1996","author":"martin","key":"ref15"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1986.1087032"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"journal-title":"Learning and sequential decision making","year":"1989","author":"barto","key":"ref5"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/BF00992702","article-title":"A reinforcement connectionist approach to robot path finding in non-mazelike environments","volume":"8","author":"del","year":"1992","journal-title":"Machine Learning"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087095"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/136035.136037"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1109\/3477.499792","article-title":"Rapid, safe, and incremental learning of navigation strategies","volume":"26","author":"del","year":"1996","journal-title":"IEEE Trans on Systems Man and Cybernetics"}],"event":{"name":"IEEE\/RSJ International Conference on Intelligent Robots and Systems. IROS '96","acronym":"IROS-96","location":"Osaka, Japan"},"container-title":["Proceedings of IEEE\/RSJ International Conference on Intelligent Robots and Systems. IROS '96"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx3\/4292\/12373\/00568991.pdf?arnumber=568991","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,15]],"date-time":"2017-06-15T12:37:54Z","timestamp":1497530274000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/ieeexplore.ieee.org\/document\/568991\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":15,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/iros.1996.568991","relation":{},"subject":[]}}