Academic Journal

Instilling moral value alignment by means of multi-objective reinforcement learning

التفاصيل البيبلوغرافية
العنوان: Instilling moral value alignment by means of multi-objective reinforcement learning
المؤلفون: Rodriguez Soto, Manel, Serramia, Marc, López Sánchez, Maite, Rodríguez-Aguilar, Juan A. (Juan Antonio)
المصدر: Articles publicats en revistes (Matemàtiques i Informàtica)
بيانات النشر: Springer
سنة النشر: 2022
المجموعة: Dipòsit Digital de la Universitat de Barcelona
مصطلحات موضوعية: Intel·ligència artificial, Aprenentatge per reforç (Intel·ligència artificial), Ètica, Aspectes morals, Artificial intelligence, Reinforcement learning, Ethics, Moral aspects
الوصف: AI research is being challenged with ensuring that autonomous agents learn to behave ethically, namely in alignment with moral values. Here, we propose a novel way of tackling the value alignment problem as a two-step process. The first step consists on formalising moral values and value aligned behaviour based on philosophical foundations. Our formalisation is compatible with the framework of (Multi-Objective) Reinforcement Learning, to ease the handling of an agent's individual and ethical objectives. The second step consists in designing an environment wherein an agent learns to behave ethically while pursuing its individual objective. We leverage on our theoretical results to introduce an algorithm that automates our two-step approach. In the cases where value-aligned behaviour is possible, our algorithm produces a learning environment for the agent wherein it will learn a value-aligned behaviour.
نوع الوثيقة: article in journal/newspaper
وصف الملف: 17 p.; application/pdf
اللغة: English
تدمد: 1388-1957
Relation: Reproducció del document publicat a: https://doi.org/10.1007/s10676-022-09635-0; Ethics And Information Technology, 2022, vol. 24; https://doi.org/10.1007/s10676-022-09635-0; http://hdl.handle.net/2445/192920; 715848
الاتاحة: http://hdl.handle.net/2445/192920
Rights: cc by (c) Manel Rodríguez Soto et al., 2022 ; http://creativecommons.org/licenses/by/3.0/es/ ; info:eu-repo/semantics/openAccess
رقم الانضمام: edsbas.64AD2730
قاعدة البيانات: BASE