{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T00:17:53Z","timestamp":1767140273465,"version":"build-2238731810"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,2,8]],"date-time":"2019-02-08T00:00:00Z","timestamp":1549584000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Life Robotics"],"published-print":{"date-parts":[[2019,9]]},"DOI":"10.1007\/s10015-019-00523-3","type":"journal-article","created":{"date-parts":[[2019,2,8]],"date-time":"2019-02-08T10:08:20Z","timestamp":1549620500000},"page":"352-359","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Multi-objective safe reinforcement learning: the relationship between multi-objective reinforcement learning and safe reinforcement learning"],"prefix":"10.1007","volume":"24","author":[{"given":"Naoto","family":"Horie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tohgoroh","family":"Matsui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koichi","family":"Moriyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsuko","family":"Mutoh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobuhiro","family":"Inuzuka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,2,8]]},"reference":[{"key":"523_CR1","volume-title":"Reinforcement learning: an introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT press, Cambridge"},{"key":"523_CR2","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s10994-010-5232-5","volume":"84","author":"P Vamplew","year":"2011","unstructured":"Vamplew P, Dazeley R, Berry A, Issabekov R, Dekker E (2011) Empirical evaluation methods for multiobjective reinforcement learning algorithms. Mach Learn 84:51\u201380","journal-title":"Mach Learn"},{"key":"523_CR3","first-page":"1437","volume":"16","author":"J Garc\u00eda","year":"2015","unstructured":"Garc\u00eda J, Fern\u00e1ndez F (2015) A comprehensive survey on safe reinforcement learning. J Mach Learn Res 16:1437\u20131480","journal-title":"J Mach Learn Res"},{"key":"523_CR4","unstructured":"Aissani N, Beldjilali, Trentesaux D (2008) Efficient and effective reactive scheduling of manufacturing system using SARSA multi-objective agents. In: Proc of the 7th Int\u2019l Conf on Modeling and Simulation, pp 698\u2013707"},{"key":"523_CR5","doi-asserted-by":"crossref","unstructured":"Van Moffaert K, Drugan MM, Now\u00e9 A (2013) Scalarized multi-objective reinforcement learning: novel design techniques. In: Proc of 2013 IEEE Sympo on Adapt Dyn Progr and Reinforce Learn, pp 191\u2013199","DOI":"10.1109\/ADPRL.2013.6615007"},{"key":"523_CR6","unstructured":"G\u00e1bor Z, Kalm\u00e1r Z, Szepesv\u00e1ri C (1998) Multi-criteria reinforcement learning. In: Proc of the 15th Int\u2019l Conf on Mach Learn, pp 197\u2013205"},{"key":"523_CR7","doi-asserted-by":"crossref","unstructured":"Barrett L, Narayanan S (2008) Learning all optimal policies with multiple criteria. In: Proc of the 25th Int\u2019l Conf on Mach Learn, pp 41\u201347","DOI":"10.1145\/1390156.1390162"},{"key":"523_CR8","first-page":"3663","volume":"15","author":"K Moffaert Van","year":"2014","unstructured":"Van Moffaert K, Now\u00e9 A (2014) Multi-objective reinforcement learning using sets of Pareto dominating policies. J Mach Learn Res 15:3663\u20133692","journal-title":"J Mach Learn Res"},{"issue":"4","key":"523_CR9","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1287\/moor.1080.0324","volume":"33","author":"A Basu","year":"2008","unstructured":"Basu A, Bhattacharyya T, Borkar VS (2008) A learning algorithm for risk-sensitive cost. Math Oper Res 33(4):880\u2013898","journal-title":"Math Oper Res"},{"issue":"1","key":"523_CR10","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1287\/moor.27.1.192.334","volume":"27","author":"VS Borkar","year":"2002","unstructured":"Borkar VS, Meyn SP (2002) Risk-sensitive optimal control for Markov decision processes with monotone cost. Math Oper Res 27(1):192\u2013209","journal-title":"Math Oper Res"},{"issue":"2","key":"523_CR11","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1287\/moor.27.2.294.324","volume":"27","author":"VS Borkar","year":"2002","unstructured":"Borkar VS (2002) Q-learning for risk-sensitive control. Math Oper Res 27(2):294\u2013311","journal-title":"Math Oper Res"},{"issue":"2\u20133","key":"523_CR12","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1023\/A:1017940631555","volume":"49","author":"O Mihatsch","year":"2002","unstructured":"Mihatsch O, Neuneier R (2002) Risk-sensitive reinforcement learning. Mach Learn 49(2\u20133):267\u2013290","journal-title":"Mach Learn"},{"issue":"3","key":"523_CR13","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1527\/tjsai.16.353","volume":"16","author":"M Sato","year":"2002","unstructured":"Sato M, Kimura H, Kobayashi S (2002) TD algorithm for the variance of return and mean-variance reinforcement learning. Trans Jpn Soc Artif Intell 16(3):353\u2013362 (in Japanese)","journal-title":"Trans Jpn Soc Artif Intell"},{"key":"523_CR14","first-page":"81","volume":"24","author":"P Geibel","year":"2005","unstructured":"Geibel P, Wysotzki F (2005) Risk-sensitive reinforcement learning applied to control under constraints. J Mach Learn Res 24:81\u2013108","journal-title":"J Mach Learn Res"},{"issue":"6","key":"523_CR15","first-page":"877","volume":"27","author":"D Takeyama","year":"2015","unstructured":"Takeyama D, Kanoh M, Matsui T, Nakamura T (2015) Obtaining robot\u2019s behavior to avoid danger by using probability based reinforcement learning. J Jpn Soc Fuzzy Theory Intell Inform 27(6):877\u2013884 (in Japanese)","journal-title":"J Jpn Soc Fuzzy Theory Intell Inform"},{"key":"523_CR16","unstructured":"Horie N, Matsui T, Moriyama K, Mutoh A, Inuzuka N (2016) Reinforcement learning based on action values combined with success probability and profit. In: Proc of the 30th Ann Conf of the Jpn Soc for Artif Intell, 1M2-4 (in Japanese)"},{"key":"523_CR17","doi-asserted-by":"crossref","unstructured":"Van Moffaert K, Drugan MM, Now\u00e9 A (2013) Hypervolume-based multi-objective reinforcement learning. In: Proc of the 7th Int\u2019l Conf on Evol Multi-Criterion Opt, pp 352\u2013366","DOI":"10.1007\/978-3-642-37140-0_28"},{"key":"523_CR18","doi-asserted-by":"crossref","unstructured":"Wiering M, Withagen M, Drugan M (2014) Model-based multi-objective reinforcement learning. In: Proc of 2014 IEEE Sympo on Adapt Dyn Progr and Reinforce Learn","DOI":"10.1109\/ADPRL.2014.7010622"},{"key":"523_CR19","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/s10994-013-5369-0","volume":"92","author":"W Wang","year":"2013","unstructured":"Wang W, Sebag M (2013) Hypervolume indicator and dominance reward based multi-objective Monte-Carlo tree search. Mach Learn 92:403\u2013429","journal-title":"Mach Learn"},{"key":"523_CR20","doi-asserted-by":"crossref","unstructured":"Zitzler E, Thiele L (1998) Multiobjective optimization using evolutionary algorithms: a comparative case study. In: Proc of the 5th Int\u2019l Conf on Parallel Problem Solving from Nature, pp 292-301","DOI":"10.1007\/BFb0056872"},{"key":"523_CR21","doi-asserted-by":"crossref","unstructured":"Auger A, Bader J, Brockhoff D, Zitzler E (2009) Theory of the hypervolume indicator: optimal \n                    \n                      \n                    \n                    $$\\mu$$\n                    \n                      \n                        \u03bc\n                      \n                    \n                  -distributions and the choice of the reference point. In: Proc of the 10th ACM SIGEVO Workshop on Found of Genetic Algorithms","DOI":"10.1145\/1527125.1527138"},{"key":"523_CR22","doi-asserted-by":"crossref","unstructured":"K\u00fcnzel S, Meyer-Nieberg S (2018) Evolving artificial neural networks for multi-objective tasks. In: Proc of the 21st Int\u2019l Conf on Appl of Evol Comput, pp 671\u2013686","DOI":"10.1007\/978-3-319-77538-8_45"}],"container-title":["Artificial Life and Robotics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10015-019-00523-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-019-00523-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10015-019-00523-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,7]],"date-time":"2020-02-07T19:23:02Z","timestamp":1581103382000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10015-019-00523-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,8]]},"references-count":22,"aliases":["10.1007\/s10015-019-00524-2"],"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,9]]}},"alternative-id":["523"],"URL":"https:\/\/doi.org\/10.1007\/s10015-019-00523-3","relation":{},"ISSN":["1433-5298","1614-7456"],"issn-type":[{"value":"1433-5298","type":"print"},{"value":"1614-7456","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,8]]},"assertion":[{"value":"10 April 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}