Journal article · 2025 · Open access

Multi-objective reinforcement learning for provably incentivising alignment with value systems

Manel Rodríguez-Soto, Roxana Rădulescu, Filippo Bistaffa, Oriol Ricart, Arnau Mayoral-Macau, Maite López-Sánchez, Juan A. Rodríguez-Aguilar, Ann Nowé

Artificial Intelligence, 351, 104460 · Published 7 December 2025 · DOI 10.1016/j.artint.2025.104460

Open full textCite this paper

In brief

“Multi-objective reinforcement learning for provably incentivising alignment with value systems” is a 2025 journal article by Manel Rodríguez-Soto and 7 co-authors, published in Artificial Intelligence. OpenAlex counts 7 citations as of 17 November 2026, which puts it in the top 3% of works published in 2025 by citations. It is open access under a CC BY licence: the full text is free to read at Artificial Intelligence.

Citations
7
Most cited in
2026 (7)
Field-weighted impact
0.98
References
63
Authors
8

Abstract

This paper addresses the problem of ensuring that autonomous learning agents align with multiple moral values. Specifically, we present the theoretical principles and algorithmic tools necessary for creating an environment where we ensure that the agent learns a behaviour aligned with multiple moral values while striving to achieve its individual objective. To address this value alignment problem, we adopt the Multi-Objective Reinforcement Learning framework and propose a novel algorithm that combines techniques from Multi-Objective Reinforcement Learning and Linear Programming. In addition, we illustrate our value alignment process with an example involving an autonomous vehicle. Here, we demonstrate that the agent learns to behave in alignment with the ethical values of safety, achievement, and comfort, with achievement representing the agent’s individual objective. Such ethical behaviour differs depending on the ordering between values. We also use a synthetic multi-objective environment to evaluate the computational costs of guaranteeing ethical learning as the number of values increases.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Rodríguez-Soto, M., Rădulescu, R., Bistaffa, F., Ricart, O., Mayoral-Macau, A., López-Sánchez, M., Rodríguez-Aguilar, J. A., & Nowé, A. (2025). Multi-objective reinforcement learning for provably incentivising alignment with value systems. Artificial Intelligence, 351, 104460. https://doi.org/10.1016/j.artint.2025.104460

MLA 9

Rodríguez-Soto, Manel, et al. “Multi-objective reinforcement learning for provably incentivising alignment with value systems.” Artificial Intelligence, vol. 351, 2025, p. 104460. https://doi.org/10.1016/j.artint.2025.104460.

Chicago

Rodríguez-Soto, Manel, Roxana Rădulescu, Filippo Bistaffa, Oriol Ricart, Arnau Mayoral-Macau, Maite López-Sánchez, Juan A. Rodríguez-Aguilar, and Ann Nowé. 2025. “Multi-objective reinforcement learning for provably incentivising alignment with value systems.” Artificial Intelligence 351: 104460. https://doi.org/10.1016/j.artint.2025.104460.

Harvard

Rodríguez-Soto, M. et al. (2025) ‘Multi-objective reinforcement learning for provably incentivising alignment with value systems’, Artificial Intelligence, 351, p. 104460. doi:10.1016/j.artint.2025.104460.

IEEE

M. Rodríguez-Soto et al., “Multi-objective reinforcement learning for provably incentivising alignment with value systems,” Artificial Intelligence, vol. 351, p. 104460, 2025, doi: 10.1016/j.artint.2025.104460.

BibTeX

@article{rodriguezsoto2025multi,
  title     = {{Multi-objective reinforcement learning for provably incentivising alignment with value systems}},
  author    = {Rodríguez-Soto, Manel and Rădulescu, Roxana and Bistaffa, Filippo and Ricart, Oriol and Mayoral-Macau, Arnau and López-Sánchez, Maite and Rodríguez-Aguilar, Juan A. and Nowé, Ann},
  journal   = {Artificial Intelligence},
  year      = {2025},
  volume    = {351},
  pages     = {104460},
  doi       = {10.1016/j.artint.2025.104460},
  url       = {https://doi.org/10.1016/j.artint.2025.104460}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics

  • value alignment
  • multi-objective reinforcement learning
  • moral values
  • linear programming
  • autonomous vehicles
  • value ordering

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Rodríguez-Soto, M., Rădulescu, R., Bistaffa, F., Ricart, O., Mayoral-Macau, A., López-Sánchez, M., Rodríguez-Aguilar, J. A., & Nowé, A. (2025). Multi-objective reinforcement learning for provably incentivising alignment with value systems. Artificial Intelligence, 351, 104460. https://doi.org/10.1016/j.artint.2025.104460

How many times has this paper been cited?

7 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Artificial Intelligence: sign in and open the full text from this page.

Who wrote this paper?

Manel Rodríguez-Soto, Roxana Rădulescu, Filippo Bistaffa, Oriol Ricart, Arnau Mayoral-Macau, Maite López-Sánchez, Juan A. Rodríguez-Aguilar, Ann Nowé.

What is the DOI of this paper?

10.1016/j.artint.2025.104460, permanently at https://doi.org/10.1016/j.artint.2025.104460. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.