{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T15:44:55Z","timestamp":1769269495969,"version":"3.49.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014,7]]},"DOI":"10.1109\/ijcnn.2014.6889738","type":"proceedings-article","created":{"date-parts":[[2014,9,10]],"date-time":"2014-09-10T14:30:33Z","timestamp":1410359433000},"page":"2323-2330","source":"Crossref","is-referenced-by-count":31,"title":["Policy gradient approaches for multi-objective sequential decision making"],"prefix":"10.1109","author":[{"given":"Simone","family":"Parisi","sequence":"first","affiliation":[]},{"given":"Matteo","family":"Pirotta","sequence":"additional","affiliation":[]},{"given":"Nicola","family":"Smacchia","sequence":"additional","affiliation":[]},{"given":"Luca","family":"Bascetta","sequence":"additional","affiliation":[]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","first-page":"372","article-title":"On the limitations of scalarisation for multi-objective reinforcement learning of pareto fronts","author":"vamplew","year":"2008","journal-title":"Advances in Artificial Intelligence"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.2166\/hydro.2013.169"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.2514\/6.2010-9042"},{"key":"16","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":"13","doi-asserted-by":"publisher","DOI":"10.1527\/tjsai.21.350"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1007\/s001860000043"},{"key":"11","article-title":"A gradientbased multiobjective optimization technique using an adaptive weighting method","author":"kazuhiro izui","year":"2013","journal-title":"Proc of 2nd World Congress of Structural and Multidisciplinary Optimization"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1145\/1389095.1389232"},{"key":"21","first-page":"1394","article-title":"Adaptive stepsize for policy gradient methods","author":"pirotta","year":"2013","journal-title":"NIPS 26 Curran Associates Inc"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2003.810758"},{"key":"20","first-page":"288","article-title":"Reinforcement learning for continuous action using stochastic gradient ascent","author":"kimura","year":"1998","journal-title":"IAS-5"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5232-5"},{"key":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"10","first-page":"3","article-title":"Directed multi-objective optimization","volume":"6","author":"brown","year":"2005","journal-title":"International Journal of Computers Systems and Signals"},{"key":"7","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1613\/jair.3987","article-title":"A survey of multi-objective sequential decisionmaking","volume":"48","author":"roijers","year":"2013","journal-title":"JAIR"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1002\/wrcr.20295"},{"key":"5","first-page":"3253","article-title":"Linear fitted-q iteration with multiple reward functions","volume":"13","author":"lizotte","year":"2012","journal-title":"J Mach Learn Res"},{"key":"4","author":"shelton","year":"2001","journal-title":"Importance Sampling for Reinforcement Learning with Multiple Objectives"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"8","first-page":"1","article-title":"Multiobjective reinforcement learning: A comprehensive overview","volume":"pp","author":"liu","year":"2013","journal-title":"IEEE T Syst Man Cy C"}],"event":{"name":"2014 International Joint Conference on Neural Networks (IJCNN)","location":"Beijing, China","start":{"date-parts":[[2014,7,6]]},"end":{"date-parts":[[2014,7,11]]}},"container-title":["2014 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6880678\/6889358\/06889738.pdf?arnumber=6889738","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,14]],"date-time":"2020-10-14T15:17:41Z","timestamp":1602688661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6889738"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/ijcnn.2014.6889738","relation":{},"subject":[],"published":{"date-parts":[[2014,7]]}}}