{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T10:37:45Z","timestamp":1761647865455,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1109\/adprl.2011.5967356","type":"proceedings-article","created":{"date-parts":[[2011,8,3]],"date-time":"2011-08-03T21:40:00Z","timestamp":1312407600000},"page":"76-83","source":"Crossref","is-referenced-by-count":8,"title":["Safe reinforcement learning in high-risk tasks through policy improvement"],"prefix":"10.1109","author":[{"given":"Francisco Javier","family":"Garcia Polo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fernando","family":"Fernandez Rebollo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"251","article-title":"A Case-Based Reasoning Approach to Imitating Robocup Players","author":"floyd","year":"0","journal-title":"Proceedings of the 21st International Florida Artificial Intelligence Research Society Conference"},{"key":"ref11","first-page":"162","article-title":"Reinforcement Learning with Bounded Risk","author":"geibel","year":"0","journal-title":"Proceedings of the 18th International Conference on Machine Learning"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1613\/jair.1666","article-title":"Risk-sensitive Reinforcement Learning Applied to Chance Constrained Control","volume":"24","author":"geibel","year":"2005","journal-title":"Journal of Artificial Intelligence Research (JAIR)"},{"key":"ref13","first-page":"143","article-title":"Safe Exploration for Reinforcement Learning","author":"alexander","year":"0","journal-title":"European Symp Artificial Neural Networks"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014739"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4471-2097-1_141"},{"key":"ref16","first-page":"75","article-title":"Learning Autonomous Helicopter Flight with Evolutionary Reinforcement Learning","author":"jos\u00e9 antonio mart\u00edn","year":"0","journal-title":"12th International Conference on Computer Aided Systems Theory (EURO-CAST)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(96)00043-3"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1613\/jair.613","article-title":"Reinforcement Learning through Evolutionary Computation","author":"moriarty","year":"1999","journal-title":"Journal on Artificial Intelligence Research (JAIR)"},{"journal-title":"Autonomous Helicopter Flight via Reinforcement Learning","year":"2003","author":"ng","key":"ref19"},{"key":"ref4","article-title":"Learning Mobile Robot Motion Control from Demonstrated Primitives and Human Feed-back","author":"argall","year":"0","journal-title":"Proceedings of the 14th International Symposium on Robotics Research (ISRR09)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1228716.1228725"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2008.4651020"},{"key":"ref8","first-page":"185","article-title":"Acquisition of Elementary Robot Skills from Human Demonstration","author":"dillmann","year":"0","journal-title":"Int Symp Intelligent Robotic Syst"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2009.06.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/0020-7373(92)90018-G"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"39","DOI":"10.3233\/AIC-1994-7104","article-title":"Case-Based Reasoning; Foundational Issues, Methodological Variations, and System Approaches","volume":"7","author":"aamodt","year":"1994","journal-title":"AI Commu-nications"},{"key":"ref9","first-page":"55","article-title":"Toward a domain-independent case-based reasoning approach for imitation: Three case studies in gaming","author":"floyd","year":"0","journal-title":"Workshop on Case-Based Reasoning for Computer Games at the 18th International Conference on Case-Based Reasoning (ICCBR)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2001.976257"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref22"},{"key":"ref21","first-page":"1040","article-title":"Learning from Demonstration","volume":"9","author":"schaal","year":"1997","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"1357","article-title":"Teaching Sequential Tasks with Repetition through Demonstration","author":"harini","year":"0","journal-title":"International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS)"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368199"}],"event":{"name":"2011 Ieee Symposium On Adaptive Dynamic Programming And Reinforcement Learning","start":{"date-parts":[[2011,4,11]]},"location":"Paris, France","end":{"date-parts":[[2011,4,15]]}},"container-title":["2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5958170\/5967347\/05967356.pdf?arnumber=5967356","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,6,21]],"date-time":"2020-06-21T20:47:35Z","timestamp":1592772455000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5967356\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/adprl.2011.5967356","relation":{},"subject":[],"published":{"date-parts":[[2011,4]]}}}