Abstract
During the first step of practical reasoning, i.e. deliberation or goals selection, an intelligent agent generates a set of pursuable goals and then selects which of them he commits to achieve. Explainable Artificial Intelligence (XAI) systems, including intelligent agents, must be able to explain their internal decisions. In the context of goals selection, agents should be able to explain the reasoning path that leads them to select (or not) a certain goal. In this article, we use an argumentation-based approach for generating explanations about that reasoning path. Besides, we aim to enrich the explanations with information about emerging conflicts during the selection process and how such conflicts were resolved. We propose two types of explanations: the partial one and the complete one and a set of explanatory schemes to generate pseudo-natural explanations. Finally, we apply our proposal to the cleaner world scenario.
Partially supported by CAPES.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Pursuable goals are also known as desires and pursued goals as intentions. In this work, we consider that both are goals at different stages of processing, like it was suggested in [5].
- 2.
An instrumental argument is structured like a tree where the nodes are planning rules whose premise is made of a set of sub-goals, resources, actions, and beliefs and its conclusion or claim is a goal, which is the goal achieved by executing the plan represented by the instrumental argument.
- 3.
Literals are atoms or negation of atoms (the negation of an atom a is denoted \(\lnot a\)).
- 4.
Hereafter, terminal incompatibility is denoted by t, resource incompatibility by r, and superfluity by s.
- 5.
For further information about how instrumental arguments are built, the reader is referred to [14].
- 6.
\(\mathtt {ARG\_INS}(g)\) denotes all the instrumental arguments that represent plans that allow to achieve g.
- 7.
- 8.
In order to better deal with goals, we map each goal to a constant in \(\mathcal {L}\).
- 9.
Minimal means that there is no \(\mathcal {S}' \subset \mathcal {S}\) such that \(\mathcal {S}\vdash h\) and consistent means that it is not the case that \(\mathcal {S}\vdash pursued(g)\) and \(\mathcal {S}\vdash \lnot pursued(g)\)Â [9].
- 10.
It is not the scope of this article to study the most adequate semantics for this context or the way to select an extension when more than one is returned by a semantics.
- 11.
Underlined characters represent the variables of the schemes, which depend on the variables of rules.
- 12.
Available at: https://github.com/henriquermonteiro/BBGP-Agent-Simulator/.
References
Amgoud, L., Devred, C., Lagasquie-Schiex, M.-C.: A constrained argumentation system for practical reasoning. In: Rahwan, I., Moraitis, P. (eds.) ArgMAS 2008. LNCS (LNAI), vol. 5384, pp. 37–56. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-00207-6_3
Anjomshoae, S., Najjar, A., Calvaresi, D., Främling, K.: Explainable agents and robots: results from a systematic literature review. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, pp. 1078–1088 (2019)
Besnard, P., Hunter, A.: Argumentation based on classical logic. In: Simari, G., Rahwan, I. (eds.) Argumentation in Artificial Intelligence, pp. 133–152. Springer, Boston (2009). https://doi.org/10.1007/978-0-387-98197-0_7
Broekens, J., Harbers, M., Hindriks, K., van den Bosch, K., Jonker, C., Meyer, J.-J.: Do you get it? User-evaluated explainable BDI agents. In: Dix, J., Witteveen, C. (eds.) MATES 2010. LNCS (LNAI), vol. 6251, pp. 28–39. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-16178-0_5
Castelfranchi, C., Paglieri, F.: The role of beliefs in goal dynamics: prolegomena to a constructive theory of intentions. Synthese 155(2), 237–263 (2007). https://doi.org/10.1007/s11229-006-9156-3
Dung, P.M.: On the acceptability of arguments and its fundamental role in nonmonotonic reasoning, logic programming and n-person games. Artif. Intell. 77(2), 321–357 (1995)
Guerrero, E., Nieves, J.C., Lindgren, H.: An activity-centric argumentation framework for assistive technology aimed at improving health. Argument Comput. 7(1), 5–33 (2016)
Harbers, M., van den Bosch, K., Meyer, J.J.: Design and evaluation of explainable BDI agents. In: 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, vol. 2, pp. 125–132. IEEE (2010)
Hunter, A.: Base logics in argumentation. In: COMMA, pp. 275–286 (2010)
Langley, P., Meadows, B., Sridharan, M., Choi, D.: Explainable agency for intelligent autonomous systems. In: Twenty-Ninth IAAI Conference, pp. 4762–4763 (2017)
MartÃnez, D.C., GarcÃa, A.J., Simari, G.R.: Progressive defeat paths in abstract argumentation frameworks. In: Lamontagne, L., Marchand, M. (eds.) AI 2006. LNCS (LNAI), vol. 4013, pp. 242–253. Springer, Heidelberg (2006). https://doi.org/10.1007/11766247_21
Modgil, S., Prakken, H.: The ASPIC+ framework for structured argumentation: a tutorial. Argument Comput. 5(1), 31–62 (2014)
Morveli-Espinoza, M., Nieves, J.C., Possebom, A., Puyol-Gruart, J., Tacla, C.A.: An argumentation-based approach for identifying and dealing with incompatibilities among procedural goals. Int. J. Approx. Reason. 105, 1–26 (2019)
Morveli-Espinoza, M.M., Nieves, J.C., Possebom, A.T., Puyol-Gruart, J., Tacla, C.A.: An argumentation-based approach for identifying and dealing with incompatibilities among procedural goals. Int. J. Approx. Reason. 105, 1–26 (2019). https://doi.org/10.1016/j.ijar.2018.10.015
Morveli-Espinoza, M., Possebom, A., Tacla, C.A.: Argumentation-based agents that explain their decisions. In: 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), pp. 467–472. IEEE (2019)
Morveli-Espinoza, M., Possebom, A.T., Puyol-Gruart, J., Tacla, C.A.: Argumentation-based intention formation process. DYNA 86(208), 82–91 (2019)
Sassoon, I., Kökciyan, N., Sklar, E., Parsons, S.: Explainable argumentation for wellness consultation. In: Calvaresi, D., Najjar, A., Schumacher, M., Främling, K. (eds.) EXTRAAMAS 2019. LNCS (LNAI), vol. 11763, pp. 186–202. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30391-4_11
Thangarajah, J., Padgham, L., Winikoff, M.: Detecting and avoiding interference between goals in intelligent agents. In: Proceedings of the 23rd International Joint Conference on Artificial Intelligence. Morgan Kaufmann Publishers (2003)
Tinnemeier, N.A.M., Dastani, M., Meyer, J.-J.C.: Goal selection strategies for rational agents. In: Dastani, M., El Fallah Seghrouchni, A., Leite, J., Torroni, P. (eds.) LADS 2007. LNCS (LNAI), vol. 5118, pp. 54–70. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-85058-8_4
Wooldridge, M.J.: Reasoning About Rational Agents. MIT Press, Cambridge (2000)
Zatelli, M.R., Hübner, J.F., Ricci, A., Bordini, R.H.: Conflicting goals in agent-oriented programming. In: Proceedings of the 6th International Workshop on Programming Based on Actors, Agents, and Decentralized Control, pp. 21–30. ACM (2016)
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
Morveli-Espinoza, M., Tacla, C.A., Jasinski, H.M.R. (2020). An Argumentation-Based Approach for Explaining Goals Selection in Intelligent Agents. In: Cerri, R., Prati, R.C. (eds) Intelligent Systems. BRACIS 2020. Lecture Notes in Computer Science(), vol 12320. Springer, Cham. https://doi.org/10.1007/978-3-030-61380-8_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-61380-8_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61379-2
Online ISBN: 978-3-030-61380-8
eBook Packages: Computer ScienceComputer Science (R0)