{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T18:49:10Z","timestamp":1790362150008,"version":"4.1.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,6]]},"DOI":"10.1109\/ijcnn.2009.5178745","type":"proceedings-article","created":{"date-parts":[[2009,8,5]],"date-time":"2009-08-05T18:59:01Z","timestamp":1249498741000},"page":"1149-1156","source":"Crossref","is-referenced-by-count":40,"title":["Using continuous action spaces to solve discrete problems"],"prefix":"10.1109","author":[{"given":"Hado","family":"van Hasselt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco A.","family":"Wiering","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"13","first-page":"17","article-title":"qv () -learning: a new on-policy reinforcement learning algorithm","author":"wiering","year":"2005","journal-title":"Proceedings of the 7th European Workshop on Reinforcement Learning"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368200"},{"key":"11","author":"watkins","year":"1989","journal-title":"Learning from delayed rewards"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155416"},{"key":"3","first-page":"317","article-title":"neural fitted q iteration - first experiences with a data efficient neural reinforcement learning method","author":"riedmiller","year":"2005","journal-title":"Proceedings of the 16th European Conference on Machine Learning (ECML'05)"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114727"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114726"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-307-3.50045-9"},{"key":"4","article-title":"on-line q-learning using connectionist sytems","volume":"166","author":"rummery","year":"1994","journal-title":"Technical Report CUED\/F-INFENG-TR"},{"key":"9","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"8","first-page":"1038","article-title":"generalization in reinforcement learning: successful examples using sparse coarse coding","author":"sutton","year":"1996","journal-title":"Advances in Neural Information Processing Systems 8"}],"event":{"name":"2009 International Joint Conference on Neural Networks (IJCNN 2009 - Atlanta)","location":"Atlanta, Ga, USA","start":{"date-parts":[[2009,6,14]]},"end":{"date-parts":[[2009,6,19]]}},"container-title":["2009 International Joint Conference on Neural Networks"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5161636\/5178557\/05178745.pdf?arnumber=5178745","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,17]],"date-time":"2017-03-17T18:55:25Z","timestamp":1489776925000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5178745\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,6]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2009.5178745","relation":{},"subject":[],"published":{"date-parts":[[2009,6]]}}}