{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T03:26:38Z","timestamp":1752981998591,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,5]]},"DOI":"10.1109\/icra.2015.7139550","type":"proceedings-article","created":{"date-parts":[[2015,7,6]],"date-time":"2015-07-06T21:20:30Z","timestamp":1436217630000},"page":"2605-2612","source":"Crossref","is-referenced-by-count":44,"title":["Efficient reinforcement learning for robots using informative simulated priors"],"prefix":"10.1109","author":[{"given":"Mark","family":"Cutler","sequence":"first","affiliation":[]},{"given":"Jonathan P.","family":"How","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"12","article-title":"Robot learning from demonstration","author":"atkeson","year":"1997","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2010.5509858"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363075"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907423"},{"key":"ref14","first-page":"2125","article-title":"Transfer learning via inter task mappings for temporal difference learning","volume":"8","author":"taylor","year":"2007","journal-title":"Journal of Machine Learning Research"},{"key":"ref15","first-page":"59","article-title":"Directed exploration in reinforcement learning with transferred knowledge","author":"mann","year":"2012","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref16","article-title":"Gaussian processes for data-efficient learning in robotics and control","author":"deisenroth","year":"2014","journal-title":"Pattern Analysis and Machine Intelligence IEEE Transactions on"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907422"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","article-title":"Markov Decision Processes: Discrete Stochastic Dynamic Programming","author":"puterman","year":"1994"},{"key":"ref19","first-page":"1031","article-title":"Model-based reinforcement learning with nearly tight exploration complexity bounds","author":"szita","year":"2010","journal-title":"International Conference on Machine Learning (ICML)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932842"},{"key":"ref3","article-title":"Autonomous inverted helicopter flight via reinforcement learning","author":"ng","year":"2004","journal-title":"Proceedings of International Symposium on Experimental Robotics"},{"key":"ref6","first-page":"1017","article-title":"Improving elevator performance using reinforcement learning","volume":"8","author":"barto","year":"1996","journal-title":"Advances in neural information processing systems"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143845"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2009.V.027","article-title":"Policy search via the signed derivative","author":"kolter","year":"2009","journal-title":"Robotics Science and Systems (RSS)"},{"key":"ref20","first-page":"465","article-title":"Pilco: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proceedings of the 28th International Conference on Machine Learning (ICML-11)"},{"article-title":"Gaussian Processes for Machine Learning","year":"2006","author":"rasmussen","key":"ref22"},{"key":"ref21","article-title":"Efficient reinforcement learning using gaussian processes","volume":"9","author":"deisenroth","year":"2010"},{"key":"ref24","article-title":"Gaussian process priors with uncertain inputs - application to multiple-step ahead time series forecasting","author":"girard","year":"2005","journal-title":"Advances in Neural Information Processing Systems 15 (NIPS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139509"}],"event":{"name":"2015 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2015,5,26]]},"location":"Seattle, WA, USA","end":{"date-parts":[[2015,5,30]]}},"container-title":["2015 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7128761\/7138973\/07139550.pdf?arnumber=7139550","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,23]],"date-time":"2017-06-23T15:12:21Z","timestamp":1498230741000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7139550\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,5]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/icra.2015.7139550","relation":{},"subject":[],"published":{"date-parts":[[2015,5]]}}}