Abstract
Value alignment has emerged in recent years as a basic principle to produce beneficial and mindful Artificial Intelligence systems. It mainly states that autonomous entities should behave in a way that is aligned with our human values. In this work, we summarize a previously developed model that considers values as preferences over states of the world and defines alignment between the governing norms and the values. We provide a use-case for this framework with the Iterated Prisoner’s Dilemma model, which we use to exemplify the definitions we review. We take advantage of this use-case to introduce new concepts to be integrated with the established framework: alignment equilibrium and Pareto optimal alignment. These are inspired on the classical Nash equilibrium and Pareto optimality, but are designed to account for any value we wish to model in the system.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Andrighetto, G., Governatori, G., Noriega, P.: Normative Multi-agent Systems, vol. 4. Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, April 2013. https://doi.org/10.4230/DFU.Vol4.12111.i
Atkinson, K., Bench-Capon, T.: States, goals and values: revisiting practical reasoning. Argument Comput. 7(2–3), 135–154 (2016). https://doi.org/10.3233/AAC-160011
Axelrod, R.M.: The Evolution of Cooperation. Basic Books, New York (1984)
BellĂą, L., Liberati, P.: Inequality Analysis: The Gini Index. Food and Agriculture Organization of the United Nations (2006). http://www.fao.org/policy-support/resources/resources-details/en/c/446282/
Chinchuluun, A., Pardalos, P., Migdalas, A., Pitsoulis, L.: Pareto Optimality Game Theory And Equilibria, vol. 17. Springer, New York (2008). https://doi.org/10.1007/978-0-387-77247-9
Cowell, F.A.: Measuring Inequality. LSE Perspectives in Economic Analysis. Oxford University Press, Oxford (2009)
Cranefield, S., Winikoff, M., Dignum, V., Dignum, F.: No pizza for you: value-based plan selection in BDI agents. In: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, pp. 178–184. International Joint Conferences on Artificial Intelligence Organization (2017). https://doi.org/10.24963/ijcai.2017/26
Gorrieri, R.: Labeled transition systems. Process Algebras for Petri Nets. MTCSAES, pp. 15–34. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-55559-1_2
Huang, L.: Nash theorem (in game theory). In: Encyclopedia of Mathematics. Springer (2002). http://www.encyclopediaofmath.org/index.php?title=Nash_theorem_(in_game_theory)&oldid=40004
Lu, Y.: Artificial intelligence: a survey on evolution, models, applications and future trends. J. Manage. Anal. 6(1), 1–29 (2019). https://doi.org/10.1080/23270012.2019.1570365
Mahmoud, M.A., Ahmad, M.S., Mohd Yusoff, M.Z., Mustapha, A.: A review of norms and normative multiagent systems. Sci. World J. 2014, 1–23 (2014). https://doi.org/10.1155/2014/684587
Miceli, M., Castelfranchi, C.: A cognitive approach to values. J. Theor. Soc. Behav. 19(2), 169–193 (1989). https://doi.org/10.1111/j.1468-5914.1989.tb00143.x, https://onlinelibrary.wiley.com/doi/abs/10.1111/j.1468-5914.1989.tb00143.x
Nowak, M.A., Sigmund, K.: Tit for tat in heterogeneous populations. Nature 355(6357), 250–253 (1992). https://doi.org/10.1038/355250a0
Osborne, M.J., Rubinstein, A.: A Course in Game Theory. MIT Press, Cambridge (2012)
Russell, S.: Provably beneficial artificial intelligence. In: The Next Step: Exponential Life. BBVA-Open Mind (2017)
Russell, S.: Human Compatible: Artificial Intelligence and the Problem of Control. Penguin LCC, New York (2019)
Schwartz, H.M.: Multi-Agent Machine Learning: A Reinforcement Approach. Wiley, New York (2014). https://doi.org/10.1002/9781118884614
Schwartz, S.H.: An overview of the Schwartz theory of basic values. Online Read. Psychol. Cult. 2(1) (2012). https://doi.org/10.9707/2307-0919.1116
Sierra, C., Osman, N., Noriega, P., Sabater-Mir, J., Perello-Moragues, A.: Value alignment: a formal approach. In: Responsible Artificial Intelligence Agents Workshop (RAIA) in AAMAS 2019 (2019)
Sullivan, S., Philip, P.: Ethical theories (2002). https://www.qcc.cuny.edu/SocialSciences/ppecorino/ETHICS_TEXT/CONTENTS.htm
Acknowledgments
This work has been supported by the AppPhil project (RecerCaixa 2017), the CIMBVAL project (funded by the Spanish government, project # TIN2017-89758-R), the EU WeNet project (H2020 FET Proactive project # 823783) and the EU TAILOR project (H2020 # 952215).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Montes, N., Sierra, C. (2021). Value-Alignment Equilibrium in Multiagent Systems. In: Heintz, F., Milano, M., O'Sullivan, B. (eds) Trustworthy AI - Integrating Learning, Optimization and Reasoning. TAILOR 2020. Lecture Notes in Computer Science(), vol 12641. Springer, Cham. https://doi.org/10.1007/978-3-030-73959-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-73959-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73958-4
Online ISBN: 978-3-030-73959-1
eBook Packages: Computer ScienceComputer Science (R0)