{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,4]],"date-time":"2026-02-04T17:37:22Z","timestamp":1770226642883,"version":"3.49.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031582042","type":"print"},{"value":"9783031582028","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-58202-8_9","type":"book-chapter","created":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T23:02:05Z","timestamp":1724713325000},"page":"145-164","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Algorithms for\u00a0Learning Value-Aligned Policies Considering Admissibility Relaxation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8853-1022","authenticated-orcid":false,"given":"Andr\u00e9s","family":"Holgado-S\u00e1nchez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4148-311X","authenticated-orcid":false,"given":"Joaqu\u00edn","family":"Arias","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8298-4178","authenticated-orcid":false,"given":"Holger","family":"Billhardt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2483-9508","authenticated-orcid":false,"given":"Sascha","family":"Ossowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"9_CR1","volume-title":"Constrained Markov Decision Processes","author":"E Altman","year":"1999","unstructured":"Altman, E.: Constrained Markov Decision Processes, vol. 7. CRC Press, Boca Raton (1999)"},{"key":"9_CR2","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1007\/s10458-011-9173-6","volume":"25","author":"T Bench-Capon","year":"2012","unstructured":"Bench-Capon, T., Atkinson, K., McBurney, P.: Using argumentation to model agent decision making in economic experiments. Auton. Agent. Multi-Agent Syst. 25, 183\u2013208 (2012)","journal-title":"Auton. Agent. Multi-Agent Syst."},{"key":"9_CR3","unstructured":"Brockman, G., et al.: OpenAI gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"9_CR4","unstructured":"Christiano, P., Leike, J., Brown, T.B., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences (2023)"},{"key":"9_CR5","unstructured":"Dalal, G., Dvijotham, K., Vecerik, M., Hester, T., Paduraru, C., Tassa, Y.: Safe exploration in continuous action spaces (2018)"},{"issue":"4","key":"9_CR6","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1109\/TKDE.2010.267","volume":"24","author":"S Das","year":"2012","unstructured":"Das, S., Egecioglu, O., El Abbadi, A.: An\u00f3nimos: an LP-based approach for anonymizing weighted social network graphs. IEEE Trans. Knowl. Data Eng. 24(4), 590\u2013604 (2012). https:\/\/doi.org\/10.1109\/TKDE.2010.267","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"9_CR7","unstructured":"Foundation, T.F.: Gymnasium (2023). https:\/\/gymnasium.farama.org"},{"key":"9_CR8","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/s10994-012-5313-8","volume":"89","author":"J F\u00fcrnkranz","year":"2012","unstructured":"F\u00fcrnkranz, J., H\u00fcllermeier, E., Cheng, W., Park, S.H.: Preference-based reinforcement learning: a formal framework and a policy iteration algorithm. Mach. Learn. 89, 123\u2013156 (2012)","journal-title":"Mach. Learn."},{"key":"9_CR9","unstructured":"Government, S.: Strategic project for economic recovery and transformation of digitalization of the water cycle. report 2022. Technical report, Ministry for the Ecological Transition and Demographic Challenge (2022)"},{"key":"9_CR10","doi-asserted-by":"publisher","unstructured":"Guo, T., Yuan, Y., Zhao, P.: Admission-based reinforcement-learning algorithm in sequential social dilemmas. Appl. Sci. 13(3) (2023). https:\/\/doi.org\/10.3390\/app13031807, https:\/\/www.mdpi.com\/2076-3417\/13\/3\/1807","DOI":"10.3390\/app13031807"},{"key":"9_CR11","unstructured":"Hasselt, H.: Double Q-learning. In: Advances in Neural Information Processing Systems, vol. 23 (2010)"},{"key":"9_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/978-3-031-43264-4_27","volume-title":"Multi-Agent Systems","author":"A Holgado-S\u00e1nchez","year":"2023","unstructured":"Holgado-S\u00e1nchez, A., Arias, J., Moreno-Rebato, M., Ossowski, S.: On admissible behaviours for goal-oriented decision-making of value-aware agents. In: Malvone, V., Murano, A. (eds.) EUMAS 2023. LNCS, vol. 14282, pp. 415\u2013424. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-43264-4_27"},{"key":"9_CR13","unstructured":"Kalweit, G., Huegle, M., Werling, M., Boedecker, J.: Deep constrained Q-learning (2020)"},{"key":"9_CR14","unstructured":"p Lera-Leri, R., Bistaffa, F., Serramia, M., Lopez-Sanchez, M., Rodriguez-Aguilar, J.: Towards pluralistic value alignment: aggregating value systems through LP-regression. In: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022, pp. 780\u2013788. International Foundation for Autonomous Agents and Multiagent Systems, Richland (2022)"},{"key":"9_CR15","doi-asserted-by":"publisher","unstructured":"Montes, N., Osman, N., Sierra, C., Slavkovik, M.: Value engineering for autonomous agents. CoRR abs\/2302.08759 (2023). https:\/\/doi.org\/10.48550\/arXiv.2302.08759","DOI":"10.48550\/arXiv.2302.08759"},{"key":"9_CR16","doi-asserted-by":"publisher","first-page":"1739","DOI":"10.1613\/jair.1.13487","volume":"74","author":"N Montes","year":"2022","unstructured":"Montes, N., Sierra, C.: Synthesis and properties of optimally value-aligned normative systems. J. Artif. Intell. Res. 74, 1739\u20131774 (2022). https:\/\/doi.org\/10.1613\/jair.1.13487","journal-title":"J. Artif. Intell. Res."},{"key":"9_CR17","volume-title":"Fair Division and Collective Welfare","author":"H Moulin","year":"2004","unstructured":"Moulin, H.: Fair Division and Collective Welfare. MIT Press, Cambridge (2004)"},{"key":"9_CR18","unstructured":"Ng, A.Y., Russell, S.J.: Algorithms for inverse reinforcement learning. In: Proceedings of the Seventeenth International Conference on Machine Learning, pp. 663\u2013670 (2000)"},{"key":"9_CR19","unstructured":"Osman, N., d\u2019Inverno, M.: A computational framework of human values for ethical AI (2023)"},{"key":"9_CR20","doi-asserted-by":"publisher","unstructured":"Perello-Moragues, A., Poch, M., Sauri, D., Popartan, L.A., Noriega, P.: Modelling domestic water use in metropolitan areas using socio-cognitive agents. Water 13(8) (2021). https:\/\/doi.org\/10.3390\/w13081024, https:\/\/www.mdpi.com\/2073-4441\/13\/8\/1024","DOI":"10.3390\/w13081024"},{"key":"9_CR21","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1016\/j.mathsocsci.2015.01.002","volume":"74","author":"L Plata-P\u00e9rez","year":"2015","unstructured":"Plata-P\u00e9rez, L., S\u00e1nchez-P\u00e9rez, J., S\u00e1nchez-S\u00e1nchez, F.: An elementary characterization of the gini index. Math. Soc. Sci. 74, 79\u201383 (2015)","journal-title":"Math. Soc. Sci."},{"key":"9_CR22","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/s10676-022-09635-0","volume":"24","author":"M Rodriguez-Soto","year":"2022","unstructured":"Rodriguez-Soto, M., Serramia, M., Lopez-Sanchez, M., Rodriguez-Aguilar, J.A.: Instilling moral value alignment by means of multi-objective reinforcement learning. Ethics Inf. Technol. 24, 9 (2022). https:\/\/doi.org\/10.1007\/s10676-022-09635-0","journal-title":"Ethics Inf. Technol."},{"issue":"1","key":"9_CR23","first-page":"11","volume":"2","author":"SH Schwartz","year":"2012","unstructured":"Schwartz, S.H.: An overview of the Schwartz theory of basic values. Online Read. Psychol. Cult. 2(1), 11 (2012)","journal-title":"Online Read. Psychol. Cult."},{"key":"9_CR24","unstructured":"Sierra, C., Osman, N., Noriega, P., Sabater-Mir, J., Perell\u00f3, A.: Value alignment: a formal approach. CoRR abs\/2110.09240 (2021). arXiv:2110.09240"},{"key":"9_CR25","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"9_CR26","unstructured":"Tessler, C., Mankowitz, D.J., Mannor, S.: Reward constrained policy optimization (2018)"},{"key":"9_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1007\/978-3-642-12805-9_5","volume-title":"Argumentation in Multi-Agent Systems","author":"TL van der Weide","year":"2010","unstructured":"van der Weide, T.L., Dignum, F., Meyer, J.J.C., Prakken, H., Vreeswijk, G.A.W.: Practical reasoning using values. In: McBurney, P., Rahwan, I., Parsons, S., Maudet, N. (eds.) ArgMAS 2009. LNCS, vol. 6057, pp. 79\u201393. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-12805-9_5"}],"container-title":["Lecture Notes in Computer Science","Value Engineering in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-58202-8_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,26]],"date-time":"2024-08-26T23:03:20Z","timestamp":1724713400000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-58202-8_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031582042","9783031582028"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-58202-8_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"VALE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Value Engineering in AI","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Krakow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Poland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"vale2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/vale2023.iiia.csic.es\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}