{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T06:56:15Z","timestamp":1729666575146,"version":"3.28.0"},"reference-count":13,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,10]]},"DOI":"10.1109\/iros.2012.6385818","type":"proceedings-article","created":{"date-parts":[[2013,1,3]],"date-time":"2013-01-03T04:15:05Z","timestamp":1357186505000},"page":"1631-1636","source":"Crossref","is-referenced-by-count":10,"title":["Adaptive exploration for continual reinforcement learning"],"prefix":"10.1109","author":[{"given":"Freek","family":"Stulp","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"11","first-page":"3137","article-title":"A generalized path integral control approach to reinforcement learning","volume":"11","author":"theodorou","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"12","article-title":"Efficient exploration in reinforcement learning","author":"thrun","year":"1992","journal-title":"Technical Report CMU-CS-92-102 Carnegie-Mellon University"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1162\/153244303765208377"},{"key":"1","article-title":"Informationgeometric optimization algorithms: A unifying picture via invariance principles","author":"arnold","year":"2011","journal-title":"Technical Report INRIA Saclay"},{"key":"10","article-title":"Path integral policy improvement with covariance matrix adaptation","author":"stulp","year":"2012","journal-title":"Proceedings of ICML"},{"key":"7","article-title":"The cross-entropy method: A unified approach to combinatorial optimization","author":"rubinstein","year":"2004","journal-title":"Monte Carlo Simulation and Machine Learning"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2007.11.026"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087548"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5223-6"},{"key":"9","article-title":"The SL simulation and real-time control software package","author":"schaal","year":"2007","journal-title":"Technical report Univ of Southern California"},{"key":"8","doi-asserted-by":"crossref","first-page":"14","DOI":"10.2478\/s13230-010-0002-4","article-title":"Exploring parameter space in reinforcement learning","volume":"1","author":"ru?ckstiess","year":"2010","journal-title":"Paladyn Journal of Behavioral Robotics"}],"event":{"name":"2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS 2012)","start":{"date-parts":[[2012,10,7]]},"location":"Vilamoura-Algarve, Portugal","end":{"date-parts":[[2012,10,12]]}},"container-title":["2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6363628\/6385431\/06385818.pdf?arnumber=6385818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,4]],"date-time":"2024-05-04T06:34:04Z","timestamp":1714804444000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6385818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/iros.2012.6385818","relation":{},"subject":[],"published":{"date-parts":[[2012,10]]}}}