Abstract
Mistrust poses a significant threat to the widespread adoption of intelligent agents. Guarantees about the behaviour of intelligent systems could help foster trust. In this paper, we investigate mechanisms to integrate value-based reasoning in practical reasoning as a way to ensure that agents actions align not only with society norms but also with user’s values. In particular, we expand a normative BDI agent architecture with an explicit representation of values.
This work was supported by UK Research and Innovation (EP/S023356/1), in the UKRI Centre for Doctoral Training in Safe and Trusted Artificial Intelligence; and the Engineering and Physical Sciences Research Council (EP/R033188/1).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
We are using a subset of the ten basic values for brevity.
- 3.
Depending on the particular domain of application, a constraint to ensure that one of \(promote(v, \gamma , 0)\) or \(demote(v, \gamma , 0)\) holds could be added to the V context.
References
Atkinson, K., Bench-Capon, T.J.M.: Taking account of the actions of others in value-based reasoning. Artif. Intell. 254, 1–20 (2018)
Bench-Capon, T., Modgil, S.: Norms and value based reasoning: justifying compliance and violation. Artif. Intell. Law 25(1), 29–64 (2017). https://doi.org/10.1007/s10506-017-9194-9
Casali, A., Godo, L., Sierra, C.: A graded BDI agent model to represent and reason about preferences. Artif. Intell. 175(7–8), 1468–1478 (2011)
Chang, R.: Value pluralism. In: International Encyclopedia of the Social & Behavioral Sciences: Second Edition, pp. 21–26. Elsevier Inc. (2015)
Cranefield, S., Winikoff, M., Dignum, V., Dignum, F.: No pizza for you: Value-based plan selection in BDI agents. In: Proceedings of IJCAI, pp. 178–184 (2017)
Criado, N., Argente, E., Noriega, P., Botti, V.J.: Reasoning about norms under uncertainty in dynamic environments. Int. J. Approx. Reason. 55(9), 2049–2070 (2014)
Criado, N., Black, E., Luck, M.: A coherence maximisation process for solving normative inconsistencies. Auton. Agents Multi Agent Syst. 30(4), 640–680 (2015). https://doi.org/10.1007/s10458-015-9300-x
Gasparini, L., Norman, T.J., Kollingbaum, M.J.: Severity-sensitive norm-governed multi-agent planning. Auton. Agents Multi Agent Syst. 32(1), 26–58 (2017). https://doi.org/10.1007/s10458-017-9372-x
Malle, B.F., Bello, P., Scheutz, M.: Requirements for an artificial agent with norm competence. In: Proceedings of AIES, pp. 21–27 (2019)
Mercuur, R., Dignum, V., Jonker, C.: The value of values and norms in social simulation. J. Artif. Soc. Soc. Simul. 22(1) (2019)
Schwartz, S.H.: An overview of the schwartz theory of basic values. Online Read. Psychol. Cult. 2(1), 11 (2012)
Serramia, M., López-Sánchez, M., Rodríguez-Aguilar, J.A., Morales, J., Wooldridge, M.J., Ansótegui, C.: Exploiting moral values to choose the right norms. In: Proceedings of AIES, pp. 264–270 (2018)
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)
Winikoff, M., Dignum, V., Dignum, F.: Why bad coffee? Explaining agent plans with valuings. In: Proceedings of SAFECOMP, pp. 521–534 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Szabo, J., Such, J.M., Criado, N. (2020). Understanding the Role of Values and Norms in Practical Reasoning. In: Bassiliades, N., Chalkiadakis, G., de Jonge, D. (eds) Multi-Agent Systems and Agreement Technologies. EUMAS AT 2020 2020. Lecture Notes in Computer Science(), vol 12520. Springer, Cham. https://doi.org/10.1007/978-3-030-66412-1_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-66412-1_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-66411-4
Online ISBN: 978-3-030-66412-1
eBook Packages: Computer ScienceComputer Science (R0)