{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T18:25:38Z","timestamp":1729621538547,"version":"3.28.0"},"reference-count":17,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,5]]},"DOI":"10.1109\/icra.2012.6225164","type":"proceedings-article","created":{"date-parts":[[2012,7,9]],"date-time":"2012-07-09T21:23:24Z","timestamp":1341869004000},"page":"4699-4704","source":"Crossref","is-referenced-by-count":4,"title":["Stunt driving via policy search"],"prefix":"10.1109","author":[{"given":"Tak Kit","family":"Lau","sequence":"first","affiliation":[]},{"given":"Yun-hui","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"17","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-6015-6","author":"shor","year":"1998","journal-title":"Nondifferentiable Optimization and Polynomial Problems"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.2514\/3.3166"},{"key":"13","article-title":"Infinite-horizon gradient-based policy search","volume":"15","author":"baxter","year":"2001","journal-title":"J of Artificial Intelligence Research"},{"key":"14","article-title":"Policy search via the signed derivative","author":"kolter","year":"0","journal-title":"Proc of Robotics Science and Systems 2009"},{"key":"11","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Proc of Advances in Neural Information Processing systems"},{"journal-title":"Policy Gradient Methods for Robot Control","year":"2003","author":"peters","key":"12"},{"key":"3","volume":"28","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"2","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2011.2155105"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509562"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2011.6161518"},{"key":"6","first-page":"345","article-title":"The price of bandit information for online optimization","volume":"20","author":"dani","year":"2008","journal-title":"Proc of Advances in Neural Information Processing systems"},{"key":"5","first-page":"697","article-title":"Nearly tight bounds for the","volume":"17","author":"kleinberg","year":"2004","journal-title":"Proc of Advances in Neural Information Processing systems"},{"key":"4","article-title":"Policy search for motor primitives in robotics","volume":"22","author":"kober","year":"2009","journal-title":"Proc of Advances in Neural Information Processing systems"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2012.6225165"},{"journal-title":"Proc of IEEE Int Conf Robot and Biom 2011","article-title":"Learning autonomous drift parking from one demonstration","year":"0","key":"8"}],"event":{"name":"2012 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2012,5,14]]},"location":"St Paul, MN, USA","end":{"date-parts":[[2012,5,18]]}},"container-title":["2012 IEEE International Conference on Robotics and Automation"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6215071\/6224548\/06225164.pdf?arnumber=6225164","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T21:07:56Z","timestamp":1497992876000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6225164\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icra.2012.6225164","relation":{},"subject":[],"published":{"date-parts":[[2012,5]]}}}