{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T01:37:56Z","timestamp":1730252276157,"version":"3.28.0"},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1109\/icnsc.2011.5874921","type":"proceedings-article","created":{"date-parts":[[2011,6,20]],"date-time":"2011-06-20T15:04:02Z","timestamp":1308582242000},"page":"260-265","source":"Crossref","is-referenced-by-count":9,"title":["Multi-objective fitted Q-iteration: Pareto frontier approximation in one single run"],"prefix":"10.1109","author":[{"given":"Andrea","family":"Castelletti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francesca","family":"Pianosi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Approximate Dynamic Programming Solving the Curses of Dimensionality","year":"2006","author":"powell","key":"ref10"},{"key":"ref11","article-title":"Online Fitted Reinforcement Learning","author":"gordon","year":"1995","journal-title":"Proceedings of the 12th International Conference on Machine Learning"},{"key":"ref12","article-title":"Adaptive Treatment of Epilepsy via Batch-mode Reinforcement Learning","author":"guez","year":"2008","journal-title":"Proc 22nd AAAI Conf Artificial Intelligence"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1029\/2009WR008898"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref15","article-title":"Reinforcement Learning in the Operational Management of a Water System","author":"castelletti","year":"2001","journal-title":"Proc IFAC Workshop on Modeling and Control in Envi Issues"},{"key":"ref16","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 European Conference on Machine Learning"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368162"},{"key":"ref18","first-page":"1177","article-title":"Fitted Q—iteration by Advantage Weighted Regression","volume":"22","author":"neumann","year":"2009","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Batch Reinforcement Learning for Controlling a Mobile Wheeled Pendulum Robot","author":"bonarini","year":"2008","journal-title":"Proc IFIP World Computer Congress"},{"key":"ref4","article-title":"Dynamic preferences in mult-criteria reinforcement learning","author":"narayanan","year":"2005","journal-title":"Proceedings of 22nd International Conference on Machine Learning"},{"key":"ref3","first-page":"325360","article-title":"A geometric approach to multi-criterion reinforcement learning","volume":"5","author":"mannor","year":"2004","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","article-title":"Efficient reinforcement learning with multiple reward functions for randomized controlled trial analysis","author":"lizotte","year":"2010","journal-title":"Proceedings of the 27th International Conference on Machine Learning"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390162"},{"journal-title":"Dynamic Programming","year":"1957","author":"bellman","key":"ref8"},{"key":"ref7","first-page":"503","article-title":"Tree-based Batch Mode Reinforcement Learning","volume":"6","author":"ernst","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref2","article-title":"Multi-criteria reinforcement learning","author":"gabor","year":"1998","journal-title":"Proceedings of 15th International Conference on Machine Learning"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/evco.2009.17.2.135"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00114724"},{"key":"ref20","article-title":"Evaluating the quality of approximations to the non-dominated set","author":"hansen","year":"1998","journal-title":"Technical report IMM-REP-1998–15"},{"key":"ref22","article-title":"Approximate solutions to markov decision processes","author":"gordon","year":"1999","journal-title":"Ph D Dissertation Computer Science Department"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-006-6226-1"}],"event":{"name":"2011 International Conference on Networking, Sensing and Control (ICNSC 2011)","start":{"date-parts":[[2011,4,11]]},"location":"Delft","end":{"date-parts":[[2011,4,13]]}},"container-title":["2011 International Conference on Networking, Sensing and Control"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5781738\/5874867\/05874921.pdf?arnumber=5874921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,3,29]],"date-time":"2018-03-29T20:31:55Z","timestamp":1522355515000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5874921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icnsc.2011.5874921","relation":{},"subject":[],"published":{"date-parts":[[2011,4]]}}}