{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T04:36:05Z","timestamp":1777523765819,"version":"3.51.4"},"reference-count":82,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T00:00:00Z","timestamp":1764892800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100018693","name":"Horizon Europe","doi-asserted-by":"publisher","award":["101060693"],"award-info":[{"award-number":["101060693"]}],"id":[{"id":"10.13039\/100018693","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"State Agency of Research","doi-asserted-by":"publisher","award":["PID2024-156022OB-C33"],"award-info":[{"award-number":["PID2024-156022OB-C33"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"State Agency of Research","doi-asserted-by":"publisher","award":["PID2024-158227NB-C31"],"award-info":[{"award-number":["PID2024-158227NB-C31"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"State Agency of Research","doi-asserted-by":"publisher","award":["IASOMMA2024"],"award-info":[{"award-number":["IASOMMA2024"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"State Agency of Research","doi-asserted-by":"publisher","award":["PID2022-136787NB-I00"],"award-info":[{"award-number":["PID2022-136787NB-I00"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"State Agency of Research","doi-asserted-by":"publisher","award":["TED2021-131295B-C31"],"award-info":[{"award-number":["TED2021-131295B-C31"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011033","name":"State Agency of Research","doi-asserted-by":"publisher","award":["PID2020-113594RB-100"],"award-info":[{"award-number":["PID2020-113594RB-100"]}],"id":[{"id":"10.13039\/501100011033","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002809","name":"Government of Catalonia","doi-asserted-by":"publisher","award":["2021 SGR 00754"],"award-info":[{"award-number":["2021 SGR 00754"]}],"id":[{"id":"10.13039\/501100002809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002809","name":"Government of Catalonia","doi-asserted-by":"publisher","award":["2021 SGR 00313"],"award-info":[{"award-number":["2021 SGR 00313"]}],"id":[{"id":"10.13039\/501100002809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004837","name":"Ministerio de Ciencia e Innovaci\u00f3n","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004837","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011878","name":"Vlaamse regering","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011878","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002913","name":"Government of Flanders","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002913","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Research Foundation Flanders","doi-asserted-by":"publisher","award":["G062819N"],"award-info":[{"award-number":["G062819N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003130","name":"Research Foundation Flanders","doi-asserted-by":"publisher","award":["1286223N"],"award-info":[{"award-number":["1286223N"]}],"id":[{"id":"10.13039\/501100003130","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Artificial Intelligence"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1016\/j.artint.2025.104460","type":"journal-article","created":{"date-parts":[[2025,12,7]],"date-time":"2025-12-07T15:11:59Z","timestamp":1765120319000},"page":"104460","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Multi-objective reinforcement learning for provably incentivising alignment with value systems"],"prefix":"10.1016","volume":"351","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1339-2018","authenticated-orcid":false,"given":"Manel","family":"Rodriguez-Soto","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1446-5514","authenticated-orcid":false,"given":"Roxana","family":"R\u0103dulescu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1658-6125","authenticated-orcid":false,"given":"Filippo","family":"Bistaffa","sequence":"additional","affiliation":[]},{"given":"Oriol","family":"Ricart","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3831-2398","authenticated-orcid":false,"given":"Arnau","family":"Mayoral-Macau","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1838-5928","authenticated-orcid":false,"given":"Maite","family":"Lopez-Sanchez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2940-6886","authenticated-orcid":false,"given":"Juan A.","family":"Rodriguez-Aguilar","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6346-4564","authenticated-orcid":false,"given":"Ann","family":"Now\u00e9","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.artint.2025.104460_bib0001","series-title":"Aligning Superintelligence with Human Interests: A Technical Research Agenda","author":"Soares","year":"2014"},{"key":"10.1016\/j.artint.2025.104460_bib0002","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1609\/aimag.v36i4.2577","article-title":"Research priorities for robust and beneficial artificial intelligence","volume":"36","author":"Russell","year":"2015","journal-title":"Ai Magazine"},{"key":"10.1016\/j.artint.2025.104460_bib0003","series-title":"Reflections on Artificial Intelligence for Humanity","first-page":"13","article-title":"Trustworthy AI","author":"Chatila","year":"2021"},{"key":"10.1016\/j.artint.2025.104460_bib0004","unstructured":"IEEE, IEEE global initiative on ethics of autonomous and intelligent systems, 2019, (https:\/\/standards.ieee.org\/industry-connections\/ec\/autonomous-systems.html). Accessed: 2024-10-31."},{"key":"10.1016\/j.artint.2025.104460_bib0005","unstructured":"E. Comission, Artificial intelligence act, 2021, (https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/?qid=1623335154975%26uri=CELEX%3A52021PC0206). Accessed: 2021-06-29."},{"key":"10.1016\/j.artint.2025.104460_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.techsoc.2021.101726","article-title":"The ethical issues of social assistive robotics: a critical literature review","volume":"67","author":"Boada","year":"2021","journal-title":"Technol. Soc."},{"key":"10.1016\/j.artint.2025.104460_bib0007","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511498466","article-title":"The Structure of Values and Norms","author":"Hansson","year":"2001"},{"key":"10.1016\/j.artint.2025.104460_bib0008","series-title":"International Conference on P2P, Parallel, Grid, Cloud and Internet Computing","first-page":"188","article-title":"Towards the design of ethically-aware pedagogical conversational agents","author":"Casas-Roma","year":"2020"},{"key":"10.1016\/j.artint.2025.104460_bib0009","series-title":"IJCAI","first-page":"5527","article-title":"Building ethics into artificial intelligence","author":"Yu","year":"2018"},{"key":"10.1016\/j.artint.2025.104460_bib0010","first-page":"9785","article-title":"Building ethically bounded AI","volume":"33","author":"Rossi","year":"2019","journal-title":"Proc. AAAI Confer. Artif. Intell."},{"key":"10.1016\/j.artint.2025.104460_bib0011","unstructured":"D. Amodei, C. Olah, J. Steinhardt, P.F. Christiano, J. Schulman, D. Man\u00e9, Concrete problems in AI safety, arXiv: 1606.06565(2016)."},{"key":"10.1016\/j.artint.2025.104460_bib0012","unstructured":"J. Leike, M. Martic, V. Krakovna, P. Ortega, T. Everitt, A. Lefrancq, L. Orseau, S. Legg, AI safety gridworlds, arXiv: 1711.09883 (2017)."},{"key":"10.1016\/j.artint.2025.104460_bib0013","doi-asserted-by":"crossref","DOI":"10.1109\/TNN.1998.712192","article-title":"Reinforcement Learning - An Introduction","author":"Sutton","year":"1998"},{"key":"10.1016\/j.artint.2025.104460_bib0014","series-title":"AAAI Workshop: AI, Ethics, and Society","article-title":"Using stories to teach human values to artificial agents","author":"Riedl","year":"2016"},{"key":"10.1016\/j.artint.2025.104460_bib0015","series-title":"AAAI Work.: AI, Ethics, and Society","article-title":"Reinforcement learning as a framework for ethical decision making","volume":"92","author":"Abel","year":"2016"},{"key":"10.1016\/j.artint.2025.104460_bib0016","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"A low-cost ethics shaping approach for designing reinforcement learning agents","volume":"32","author":"Wu","year":"2018"},{"key":"10.1016\/j.artint.2025.104460_bib0017","first-page":"6377","article-title":"Teaching AI agents ethical values using reinforcement learning and policy orchestration","volume":"PP","author":"Noothigattu","year":"2019","journal-title":"IBM J. Res. Dev."},{"key":"10.1016\/j.artint.2025.104460_bib0018","first-page":"3","article-title":"Incorporating behavioral constraints in online AI systems","volume":"33","author":"Balakrishnan","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.artint.2025.104460_bib0019","series-title":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21","first-page":"545","article-title":"Multi-objective reinforcement learning for designing ethical environments","author":"Rodriguez-Soto","year":"2021"},{"key":"10.1016\/j.artint.2025.104460_bib0020","series-title":"Value Pluralism and Ethical Choice","author":"Cooper","year":"1993"},{"key":"10.1016\/j.artint.2025.104460_bib0021","series-title":"The Right and the Good Some Problems in Ethics","author":"Ross","year":"1930"},{"key":"10.1016\/j.artint.2025.104460_bib0022","series-title":"Principles of Biomedical Ethics \/ Tom L. Beauchamp, James F. Childress","author":"Beauchamp","year":"1979"},{"key":"10.1016\/j.artint.2025.104460_bib0023","series-title":"Ethics, Technology, and Engineering: An Introduction","author":"van de Poel","year":"2011"},{"key":"10.1016\/j.artint.2025.104460_bib0024","doi-asserted-by":"crossref","unstructured":"S. Schwartz, An Overview of the Schwartz Theory of Basic Values, 10.9707\/2307-0919.1116, Online Readings in Psychology and Culture, 2, pp. 11\u201320Jerusalem Hebrew University (2012).","DOI":"10.9707\/2307-0919.1116"},{"key":"10.1016\/j.artint.2025.104460_bib0025","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-01576-2","article-title":"Multi-Objective Decision Making","author":"Roijers","year":"2017"},{"key":"10.1016\/j.artint.2025.104460_bib0026","first-page":"1","article-title":"Multi-objective multi-agent decision making: a utility-based analysis and survey","volume":"34","author":"R\u0103dulescu","year":"2019","journal-title":"Auton. Agent Multi. Agent Syst."},{"key":"10.1016\/j.artint.2025.104460_bib0027","article-title":"Modeling ethical and operational preferences in automated driving systems","volume":"19","author":"Caballero","year":"2021","journal-title":"Decis. Anal."},{"issue":"5","key":"10.1016\/j.artint.2025.104460_bib0028","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1002\/asmb.2765","article-title":"Some statistical challenges in automated driving systems","volume":"39","author":"Caballero","year":"2023","journal-title":"Appl. Stoch. Models Bus. Ind."},{"key":"10.1016\/j.artint.2025.104460_bib0029","first-page":"279","article-title":"Q-learning","volume":"8","author":"Watkins","year":"1992","journal-title":"Mach. Learn."},{"key":"10.1016\/j.artint.2025.104460_bib0030","series-title":"Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems","doi-asserted-by":"crossref","first-page":"1110","DOI":"10.65109\/NPXB3014","article-title":"Pareto conditioned networks","author":"Reymond","year":"2022"},{"key":"10.1016\/j.artint.2025.104460_bib0031","doi-asserted-by":"crossref","DOI":"10.1007\/s10676-022-09635-0","article-title":"Instilling moral value alignment by means of multi-objective reinforcement learning","volume":"24","author":"Rodriguez-Soto","year":"2022","journal-title":"Ethics Inf. Technol."},{"issue":"5","key":"10.1016\/j.artint.2025.104460_bib0032","first-page":"679","article-title":"A Mrkovian decision process","volume":"6","author":"BELLMAN","year":"1957","journal-title":"J. Math. Mech."},{"issue":"1","key":"10.1016\/j.artint.2025.104460_bib0033","first-page":"237","article-title":"Reinforcement learning: a survey","volume":"4","author":"Kaelbling","year":"1996","journal-title":"J. Artif. Int. Res."},{"issue":"1","key":"10.1016\/j.artint.2025.104460_bib0034","first-page":"67","article-title":"A survey of multi-objective sequential decision-making","volume":"48","author":"Roijers","year":"2013","journal-title":"J. Artif. Int. Res."},{"key":"10.1016\/j.artint.2025.104460_bib0035","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/s10994-010-5232-5","article-title":"Empirical evaluation methods for multiobjective reinforcement learning algorithms","volume":"84","author":"Vamplew","year":"2011","journal-title":"Mach. Learn."},{"key":"10.1016\/j.artint.2025.104460_bib0036","series-title":"Modelling and Control in Environmental Issues","article-title":"Reinforcement learning in the operational management of a water system","author":"Castelletti","year":"2002"},{"key":"10.1016\/j.artint.2025.104460_bib0037","series-title":"Proceedings of the 22nd International Conference on Machine Learning","first-page":"601","article-title":"Dynamic preferences in multi-criteria reinforcement learning","author":"Natarajan","year":"2005"},{"key":"10.1016\/j.artint.2025.104460_bib0038","first-page":"41","article-title":"Learning all optimal policies with multiple criteria","author":"Barrett","year":"2008","journal-title":"Proc. 25th Int. Conf. Mach. Learn."},{"issue":"1","key":"10.1016\/j.artint.2025.104460_bib0039","first-page":"3483","article-title":"Multi-objective reinforcement learning using sets of pareto dominating policies","volume":"15","author":"Van Moffaert","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.artint.2025.104460_bib0040","series-title":"AAAI Workshops","article-title":"Value alignment or misalignment - what will keep systems accountable?","author":"Arnold","year":"2017"},{"key":"10.1016\/j.artint.2025.104460_bib0041","doi-asserted-by":"crossref","first-page":"411","DOI":"10.1007\/s11023-020-09539-2","article-title":"Artificial intelligence, values, and alignment","volume":"30","author":"Gabriel","year":"2020","journal-title":"Minds Mach."},{"key":"10.1016\/j.artint.2025.104460_bib0042","doi-asserted-by":"crossref","first-page":"54","DOI":"10.11590\/abhps.2020.2.04","article-title":"Challenges of aligning artificial intelligence with human values","volume":"8","author":"Sutrop","year":"2020","journal-title":"Acta Baltica Historiae et Philosophiae Scientiarum"},{"key":"10.1016\/j.artint.2025.104460_bib0043","series-title":"The Stanford Encyclopedia of Philosophy","article-title":"Value pluralism","author":"Mason","year":"2023"},{"key":"10.1016\/j.artint.2025.104460_bib0044","series-title":"Proceedings of the 1st Conference on Artificial Intelligence, Ethics and Society (AIES\u201918)","first-page":"1","article-title":"Exploiting moral values to choose the right norms","author":"Serramia","year":"2018"},{"key":"10.1016\/j.artint.2025.104460_bib0045","series-title":"Responsible Artif. Intell. Agents Workshop (RAIA) AAMAS 2019","article-title":"Value alignment: a formal approach","author":"Sierra","year":"2019"},{"key":"10.1016\/j.artint.2025.104460_bib0046","series-title":"Argumentation in Artificial Intelligence","first-page":"45","article-title":"Abstract argumentation and values","author":"Bench-Capon","year":"2009"},{"key":"10.1016\/j.artint.2025.104460_bib0047","series-title":"AAMAS 2017 Workshops, Best Papers.","first-page":"1","article-title":"Reasoning about opportunistic propensity in multi-agent systems","author":"Luo","year":"2017"},{"issue":"2","key":"10.1016\/j.artint.2025.104460_bib0048","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10458-021-09519-5","article-title":"On the dominant set selection problem and its application to value alignment","volume":"35","author":"Serramia","year":"2021","journal-title":"Auton. Agent Multi Agent Syst."},{"key":"10.1016\/j.artint.2025.104460_bib0049","series-title":"Principles of biomedical ethics","author":"Beauchamp","year":"2019"},{"key":"10.1016\/j.artint.2025.104460_bib0050","article-title":"Multi-objective MDPs with conditional lexicographic reward preferences","volume":"29","author":"Wray","year":"2015","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"10.1016\/j.artint.2025.104460_bib0051","series-title":"CRC Concise Encyclopedia of Mathematics","author":"Weisstein","year":"2002"},{"key":"10.1016\/j.artint.2025.104460_bib0052","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s10458-022-09552-y","article-title":"A practical guide to multi-objective reinforcement learning and planning","volume":"36","author":"Hayes","year":"2022","journal-title":"Auton. Agent Multi. Agent Syst."},{"issue":"6","key":"10.1016\/j.artint.2025.104460_bib0053","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1109\/MIS.2003.1249168","article-title":"Computational-Mechanism design: a call to arms","volume":"18","author":"Dash","year":"2003","journal-title":"IEEE Intell. Syst."},{"key":"10.1016\/j.artint.2025.104460_bib0054","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2021.104186","article-title":"Potential-based multiobjective reinforcement learning approaches to low-impact agents for AI safety","volume":"100","author":"Vamplew","year":"2021","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.artint.2025.104460_bib0055","series-title":"Proceedings of the Fourth Annual Symposium on Computational Geometry","first-page":"1","article-title":"Applications of random sampling in computational geometry, II","author":"Clarkson","year":"1988"},{"key":"10.1016\/j.artint.2025.104460_bib0056","unstructured":"Ethics_Unwrapped, Bounded ethicality, 2024a, (https:\/\/ethicsunwrapped.utexas.edu\/glossary\/bounded-ethicalitya). Accessed: 2024-06-11."},{"key":"10.1016\/j.artint.2025.104460_bib0057","unstructured":"Ethics_Unwrapped, Self-serving bias, 2024b, (https:\/\/ethicsunwrapped.utexas.edu\/glossary\/self-serving-biasb). Accessed: 2024-06-11."},{"key":"10.1016\/j.artint.2025.104460_bib0058","series-title":"Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems","doi-asserted-by":"crossref","first-page":"2486","DOI":"10.65109\/WBLF9522","article-title":"Ethical Markov decision processes with moral worth as rewards","author":"Stojanovski","year":"2024"},{"key":"10.1016\/j.artint.2025.104460_bib0059","series-title":"Proceedings of the 34th Benelux Conference on Artificial Intelligence BNAIC\/Benelearn 2022","article-title":"MO-Gym: a library of multi-objective reinforcement learning environments","author":"Alegre","year":"2022"},{"key":"10.1016\/j.artint.2025.104460_bib0060","series-title":"Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track","article-title":"A toolkit for reliable benchmarking and research in multi-objective reinforcement learning","author":"Felten","year":"2023"},{"issue":"1","key":"10.1016\/j.artint.2025.104460_bib0061","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.artint.2025.104460_bib0062","series-title":"Neurips 2018","article-title":"A Lyapunov-based approach to safe reinforcement learning","author":"Chow","year":"2018"},{"key":"10.1016\/j.artint.2025.104460_bib0063","unstructured":"V. Krakovna, L. Orseau, M. Martic, S. Legg, Penalizing side effects using stepwise relative reachability, arXiv: 1806.0118610.48550\/arXiv.1806.01186(2019)."},{"key":"10.1016\/j.artint.2025.104460_bib0064","series-title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","first-page":"354","article-title":"A multi-objective approach to mitigate negative side effects","author":"Saisubramanian","year":"2020"},{"key":"10.1016\/j.artint.2025.104460_bib0065","series-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence","article-title":"Safe reinforcement learning via shielding","author":"Alshiekh","year":"2018"},{"key":"10.1016\/j.artint.2025.104460_bib0066","series-title":"Proceedings of the 20th International Conference on Autonomous Agents and Multi-Agent Aystems (AAMAS 2021)","article-title":"Safe multi-agent reinforcement learning via shielding","author":"Elsayed-Aly","year":"2021"},{"key":"10.1016\/j.artint.2025.104460_bib0067","series-title":"Proceedings of the 20th International Joint Conference on Artificial Intelligence","article-title":"Axies: identifying and evaluating context-specific values","author":"Liscio","year":"2021"},{"key":"10.1016\/j.artint.2025.104460_bib0068","series-title":"Proceedings of the 35th AAAI International Conference on Artificial Intelligence","article-title":"Ethically compliant sequential decision making","author":"Svegliato","year":"2021"},{"key":"10.1016\/j.artint.2025.104460_bib0069","series-title":"Proceedings of the 4th Conference on AI, Ethics, and Society (AIES)","article-title":"Ethically compliant sequential decision making","author":"Nashed","year":"2021"},{"key":"10.1016\/j.artint.2025.104460_bib0070","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"2926","article-title":"Reinforcement learning under moral uncertainty","volume":"139","author":"Ecoffet","year":"2021"},{"key":"10.1016\/j.artint.2025.104460_bib0071","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s10676-006-0004-4","article-title":"Artificial morality: top-down, bottom-up, and hybrid approaches","volume":"7","author":"Allen","year":"2005","journal-title":"Ethics Inf. Technol."},{"issue":"6","key":"10.1016\/j.artint.2025.104460_bib0072","doi-asserted-by":"crossref","DOI":"10.1145\/3419633","article-title":"Implementations in machine ethics: a survey","volume":"53","author":"Tolmeijer","year":"2021","journal-title":"ACM Comput. Surv."},{"issue":"1","key":"10.1016\/j.artint.2025.104460_bib0073","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18564\/jasss.3929","article-title":"The value of values and norms in social simulation","volume":"22","author":"Mercuur","year":"2019","journal-title":"J. Artif. Soc. Social Simul."},{"key":"10.1016\/j.artint.2025.104460_bib0074","series-title":"Introduction to Formal Philosophy","author":"Hansson","year":"2018"},{"key":"10.1016\/j.artint.2025.104460_bib0075","series-title":"The Cambridge Dictionary of Philosophy","author":"Audi","year":"1999"},{"key":"10.1016\/j.artint.2025.104460_bib0076","series-title":"Proceedings of the First International Conference on Hybrid Human-Artificial Intelligence","first-page":"1","article-title":"Estimating value preferences in a hybrid participatory system","author":"Siebert","year":"2022"},{"key":"10.1016\/j.artint.2025.104460_bib0077","series-title":"Proceedings of the Twenty-first International Conference on Machine Learning","first-page":"1","article-title":"Apprenticeship learning via inverse reinforcement learning","author":"Abbeel","year":"2004"},{"key":"10.1016\/j.artint.2025.104460_bib0078","series-title":"Advances in Neural Information Processing Systems 29","first-page":"3909","article-title":"Cooperative inverse reinforcement learning","author":"Hadfield-Menell","year":"2016"},{"key":"10.1016\/j.artint.2025.104460_bib0079","series-title":"Adaptive and Learning Agents Workshop (AAMAS 2025)","article-title":"Designing ethical environments using multi-agent reinforcement learning","author":"Mayoral-Macau","year":"2025"},{"key":"10.1016\/j.artint.2025.104460_bib0080","doi-asserted-by":"crossref","DOI":"10.1007\/s10676-017-9440-6","article-title":"Human-aligned artificial intelligence is a multiobjective problem","volume":"20","author":"Vamplew","year":"2018","journal-title":"Ethics Inf. Technol."},{"key":"10.1016\/j.artint.2025.104460_bib0081","series-title":"Mitigating Negative Side Effects via Environment Shaping","first-page":"1640","author":"Saisubramanian","year":"2021"},{"key":"10.1016\/j.artint.2025.104460_bib0082","series-title":"Proceedings of the 38th International Conference on Neural Information Processing Systems","article-title":"An analytical study of utility functions in multi-objective reinforcement learning","author":"Rodriguez-Soto","year":"2025"}],"container-title":["Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370225001791?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0004370225001791?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T05:55:20Z","timestamp":1773899720000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0004370225001791"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":82,"alternative-id":["S0004370225001791"],"URL":"https:\/\/doi.org\/10.1016\/j.artint.2025.104460","relation":{},"ISSN":["0004-3702"],"issn-type":[{"value":"0004-3702","type":"print"}],"subject":[],"published":{"date-parts":[[2026,2]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-objective reinforcement learning for provably incentivising alignment with value systems","name":"articletitle","label":"Article Title"},{"value":"Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.artint.2025.104460","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104460"}}