Abstract
The emerging field of value awareness engineering claims that software agents and systems should be value-aware, i.e. they should be able to explicitly reason about the value-alignment of their actions. Values are often modelled as preferences over states or actions which are then extended to plans. In this paper, we examine the effect of different groundings of values depending on context and claim that they can be used to prune the space of courses of actions that are aligned with them. We put forward several notions of such value-admissible behaviours and illustrate them in the domain of water distribution.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Original definition from Montes and Sierra [9] assumes that the range of all value semantics functions is bounded in \([-1,1]\), so \(f_v(s)\approx \) \(-1,0,+1\) indicates that state s strongly opposes, is neutral or strongly promotes the value v, respectively. This would represent an (unnecessary strict) absolute value promotion metric.
- 2.
Note that the \([-1,1]\)-bounded semantics function used in [9] is defined in terms of the Gini index, i.e., \(f_{eq} = 1 - 2 \cdot GI(s)\). Similarly, the rest of the semantics functions we have enumerated can be bounded to that interval if needed. For this theory, we just consider these functions as quantifiers of value preorders.
- 3.
Council of Europe Parliamentary Assembly Resolution No. 1693 (2009).
- 4.
SDG 6 of the United Nations 2030 Agenda for Sustainable Development https://www.un.org/sustainabledevelopment.
- 5.
- 6.
In agriculture (https://www.bancomundial.org/es/topic/water-in-agriculture).
- 7.
Statistics on Water Supply and Sanitation Year 2020, see https://www.ine.es/prensa/essa_2020.pdf.
- 8.
Royal Decree 1/2001, of July 20, approving the Revised Text of the Water Law, Article 60.
- 9.
Royal Decree 3/2023, of January 10, establishing the technical-sanitary criteria for the quality of drinking water, its control, and supply, Article 9.
- 10.
Royal Decree 1/2001, of July 20, approving the Revised Text of the Water Law, Article 14.
References
Arnold, T., Kasenberg, D., Scheutz, M.: Value alignment or misalignment - what will keep systems accountable? In: AAAI Workshop on AI, Ethics, and Society (2017)
Christiano, P., Leike, J., Brown, T.B., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences (2023)
Fürnkranz, J., Hüllermeier, E., Cheng, W., Park, S.H.: Preference-based reinforcement learning: a formal framework and a policy iteration algorithm. Mach. Learn. 89, 123–156 (2012). https://doi.org/10.1007/s10994-012-5313-8
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)
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. www.mdpi.com/2076-3417/13/3/1807
Jiang, J., Lu, Z.: Learning fairness in multi-agent systems. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Lera-Leri, R., Bistaffa, F., Serramia, M., Lopez-Sanchez, M., Rodriguez-Aguilar, J.: Towards pluralistic value alignment: aggregating value systems through \(l_p\)-regression. In: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022, Richland, SC, pp. 780–788. International Foundation for Autonomous Agents and Multiagent Systems (2022)
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
Montes, N., Sierra, C.: Synthesis and properties of optimally value-aligned normative systems. J. Artif. Intell. Res. 74, 1739–1774 (2022). https://doi.org/10.1613/jair.1.13487
Ng, A.Y., Russell, S.J.: Algorithms for inverse reinforcement learning. In: Proceedings of the Seventeenth International Conference on Machine Learning, pp. 663–670 (2000)
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. www.mdpi.com/2073-4441/13/8/1024
Plata-Pérez, L., Sánchez-Pérez, J., Sánchez-Sánchez, F.: An elementary characterization of the Gini index. Math. Soc. Sci. 74, 79–83 (2015)
PricewaterhouseCoopers: La gestión del agua en españa. análisis y retos del ciclo urbano del agua (2018). www.pwc.es/es/publicaciones/energia/assets/gestion-agua-2018-espana.pdf
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
Sierra, C., Osman, N., Noriega, P., Sabater-Mir, J., Perelló, A.: Value alignment: a formal approach. CoRR abs/2110.09240 (2021). arxiv.org/abs/2110.09240
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)
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 (LNAI), vol. 6057, pp. 79–93. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-12805-9_5
Acknowledgements.
This work has been supported by grant VAE: TED2021-131295B-C33 funded by MCIN/AEI/ 10.13039/501100011033 and by the “European Union NextGenerationEU/PRTR”, by grant COSASS: PID2021-123673OB-C32 funded by MCIN/AEI/ 10.13039/501100011033 and by “ERDF A way of making Europe”, and by the AGROBOTS Project of Universidad Rey Juan Carlos funded by the Community of Madrid, Spain.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Holgado-Sánchez, A., Arias, J., Moreno-Rebato, M., Ossowski, S. (2023). On Admissible Behaviours for Goal-Oriented Decision-Making of Value-Aware Agents. In: Malvone, V., Murano, A. (eds) Multi-Agent Systems. EUMAS 2023. Lecture Notes in Computer Science(), vol 14282. Springer, Cham. https://doi.org/10.1007/978-3-031-43264-4_27
Download citation
DOI: https://doi.org/10.1007/978-3-031-43264-4_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-43263-7
Online ISBN: 978-3-031-43264-4
eBook Packages: Computer ScienceComputer Science (R0)