Document type
Conference objectVersion
Published versionPublication date
All rights reserved
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/217805
Multi-Objective Reinforcement Learning for Designing Ethical Environments
Journal Title
Director/Tutor
Journal ISSN
Volume Title
Related resource
Abstract
AI research is being challenged with ensuring that autonomous agents learn to behave ethically, namely in alignment with moral values. A common approach, founded on the exploitation of Reinforcement Learning techniques, is to design environments that incentivise agents to behave ethically. However, to the best of our knowledge, current approaches do not theoretically guarantee that an agent will learn to behave ethically. Here, we make headway along this direction by proposing a novel way of designing environments wherein it is formally guaranteed that an agent learns to behave ethically while pursuing its individual objectives. Our theoretical results develop within the formal framework of Multi-Objective Reinforcement Learning to ease the handling of an agent's individual and ethical objectives. As a further contribution, we leverage on our theoretical results to introduce an algorithm that automates the design of ethical environments.
Subject (English)
Citation
Citation
RODRÍGUEZ SOTO, Manel, LÓPEZ SÁNCHEZ, Maite and RODRÍGUEZ-AGUILAR, Juan A. (Juan Antonio). Multi-Objective Reinforcement Learning for Designing Ethical Environments. Comunicació a: 30th International Joint Conference on Artificial Intelligence (IJCAI 2021). [consulted: 19 of August of 2026]. Available at: https://hdl.handle.net/2445/217805