{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:35:52Z","timestamp":1780418152097,"version":"3.54.1"},"reference-count":47,"publisher":"IBM","issue":"4\/5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IBM J. Res. & Dev."],"published-print":{"date-parts":[[2019,7,1]]},"DOI":"10.1147\/jrd.2019.2945271","type":"journal-article","created":{"date-parts":[[2019,10,4]],"date-time":"2019-10-04T15:58:31Z","timestamp":1570204711000},"page":"1:1-1:13","source":"Crossref","is-referenced-by-count":12,"title":["Using multi-armed bandits to learn ethical priorities for online AI systems"],"prefix":"10.1147","volume":"63","author":[{"given":"A.","family":"Balakrishnan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D.","family":"Bouneffouf","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"N.","family":"Mattei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"F.","family":"Rossi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"3082","reference":[{"key":"ref39","first-page":"817","article-title":"The Epoch–Greedy algorithm for contextual multi-armed bandits","author":"langford","year":"2008","journal-title":"Proc 20th Int Conf Neural Inf Process Syst"},{"key":"ref38","first-page":"54","article-title":"Reinforcement learning as a framework for ethical decision making","author":"abel","year":"2016","journal-title":"Proc Workshops 30th AAAI AI Ethics Soc"},{"key":"ref33","article-title":"Choice, ordering and morality","author":"sen","year":"1974","journal-title":"Practical Reason"},{"key":"ref32","first-page":"1254","article-title":"Conservative bandits","author":"wu","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref31","first-page":"1046","article-title":"Multi-armed bandit problems with history","author":"shivaswamy","year":"2012","journal-title":"Proc 15th Int Conf Artif Intell Statist"},{"key":"ref30","first-page":"1468","author":"bouneffouf","year":"0","journal-title":"Proc 26th Int Joint Conf Artif Intell"},{"key":"ref37","article-title":"Motivated value selection for artificial agents","author":"armstrong","year":"0","journal-title":"Proc Workshops 29th Artif Intell Ethics"},{"key":"ref36","first-page":"32","article-title":"Sorry, I can't do that”: Developing mechanisms to appropriately reject directives in human–robot interactions","author":"briggs","year":"0","journal-title":"Proc AAAI Fall Symp AI Human–Robot Interaction"},{"key":"ref35","article-title":"AI safety gridworlds","author":"leike","year":"2017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaf2654"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511978036"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3278721.3278723"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.1201\/9781351251389-18","article-title":"Value alignment via tractable preference distance","author":"loreggia","year":"2018","journal-title":"Artificial Intelligence Safety and Security"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10676-006-0004-4"},{"key":"ref14","first-page":"420","article-title":"Matroid bandits: Fast combinatorial optimization with learning","author":"kveton","year":"2014","journal-title":"Proc 30th UAI"},{"key":"ref15","first-page":"3450","article-title":"Linear contextual bandits with knapsacks","author":"agrawal","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019785"},{"key":"ref17","first-page":"6377","article-title":"Teaching AI agents ethical values using reinforcement learning and policy orchestration","author":"noothigattu","year":"2019","journal-title":"Proc Int Joint Artif Intell Conf"},{"key":"ref18","first-page":"1773","article-title":"Teaching social behavior through human reinforcement for ad hoc teamwork-the STAR framework","author":"alkoby","year":"2019","journal-title":"Proc Int Conf Auton Agents and Multi Agent Syst"},{"key":"ref19","article-title":"Value alignment or misalignment—What will keep systems accountable?","author":"thomas","year":"0","journal-title":"Proc AI Ethics Soc Workshop"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1214\/14-STS504"},{"key":"ref27","first-page":"208","article-title":"Contextual bandits with linear payoff functions","author":"chu","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref3","first-page":"325","article-title":"Bandits and recommender systems","author":"mary","year":"0","journal-title":"Proc Int Workshop Mach Learn Optim Big Data"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"ref29","first-page":"433","article-title":"Algorithms with logarithmic or sublinear regret for constrained contextual bandits","author":"wu","year":"2015","journal-title":"Proc 29th Annu Conf Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/779"},{"key":"ref7","first-page":"127","article-title":"Thompson sampling for contextual bandits with linear payoffs","author":"agrawal","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/843"},{"key":"ref9","author":"wallach","year":"2008","journal-title":"Moral Machines Teaching Robots Right from Wrong"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v36i4.2577"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.2661896"},{"key":"ref20","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1001\/jama.296.15.1858"},{"key":"ref22","first-page":"39.1","article-title":"Analysis of thompson sampling for the multi-armed bandit problem","author":"agrawal","year":"0","journal-title":"Proc 25th Annu Conf Learn Theory"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013"},{"key":"ref21","author":"sutton","year":"2017","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72079-9_9"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/25.3-4.285"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1345448.1345465"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/978-3-642-34106-9_18","article-title":"Thompson sampling: An asymptotically optimal finite time analysis","author":"kaufmann","year":"2012","journal-title":"Proc 23rd Algorithmic Learn Theory"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1001\/archinte.167.13.1414"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"ref43","author":"jobber","year":"2012","journal-title":"Principles and Practice of Marketing"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1018960107028"}],"container-title":["IBM Journal of Research and Development"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5288520\/8895606\/08859302.pdf?arnumber=8859302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T17:57:47Z","timestamp":1761242267000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8859302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,7,1]]},"references-count":47,"journal-issue":{"issue":"4\/5"},"URL":"https:\/\/doi.org\/10.1147\/jrd.2019.2945271","relation":{},"ISSN":["0018-8646","0018-8646"],"issn-type":[{"value":"0018-8646","type":"print"},{"value":"0018-8646","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,7,1]]}}}