Abstract
As agent-based systems have been growing, more and more the general public has access to them and is influenced by decisions taken by these systems. This increases the necessity for such systems to be capable of explaining themselves to a user. The Beliefs-Desires-Intentions (BDI) is a commonly used agent model that has an two-phase internal goal selection process (desires and intentions) to decide what goals to pursue. Belief-based goal processing (BBGP) model is an extended-BDI model whose selection process consists of four phases. This more-grained behavior may have relevant consequences for the analysis of what an intention is and better explain how an intention becomes what it is. Contrastive explanations are commonly employed by people and can bring benefits to the explanation exchange process. A Property-contrast (P-contrast) explanation is a type of contrastive explanation that compares the properties of an explanation object. Thus, we can take a goal as the object about which we want an explanation and its status in the selection process (that is, how much it has advanced) as a property. This work tackles the problem of generating P-contrast explanations and proposes a method to construct them. The method consists of two phases, which in turn consist of a set of steps. The first step of the second phase returns a set of beliefs that constitute a future explanation. Thus, this work focuses on the first phase and the first step of the second phase. We use a scenario of the cleaner world in order to illustrate the performance of our proposal.
Supported by organization CAPES/Brazil and CNPq Proc. 409523/2021-6.
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.
A literal is either an atomic formula or the negation of an atomic formula. When a literal is an atomic formula, we say that it is a positive literal, and when a literal is the negation of an atomic formula, we say it is a negative literal.
- 2.
For more details about the BBGP model, the reader is referred to [10].
References
Bratman, M.: Intention, Plans, and Practical Reason (1987)
Castelfranchi, C., Paglieri, F.: The role of beliefs in goal dynamics: Prolegomena to a constructive theory of intentions. Synthese 155, 237–263 (2007)
Gajcin, J., Nair, R., Pedapati, T., Marinescu, R., Daly, E., Dusparic, I.: Contrastive explanations for comparing preferences of reinforcement learning. In: AAAI Conference on Artificial Intelligence (2022)
Grice, H.P.: Logic and conversation. In: [Cole, P., Morgan, J.L. (eds.) Syntax and Semantics, vol. 3, Speech Acts (1975)]
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)
Josephson, J.R., Josephson, S.G.: Abductive Inference: Computation, Philosophy, Technology. Cambridge University Press (1996)
Kaptein, F., Broekens, J., Hindriks, K., Neerincx, M.: The role of emotion in self-explanations by cognitive agents. In: 2017 Seventh International Conference on Affective Computing and Intelligent Interaction Workshops and Demos (ACIIW), pp. 88–93. IEEE (2017)
Miller, T.: Contrastive explanation: a structural-model approach. Knowl. Eng. Rev. 36, e14 (2021)
Miller, T., Howe, P., Sonenberg, L.: Explainable AI: beware of inmates running the asylum or: how i learnt to stop worrying and love the social and behavioural sciences. arXiv preprint arXiv:1712.00547 (2017)
Morveli-Espinoza, M., Nieves, J.C., Tacla, C.A., Jasinski, H.M.: An argumentation-based approach for goal reasoning and explanations generation. J. Logic Comput. 105, 1–26 (2022)
Morveli-Espinoza, M., Possebom, A.T., Tacla, C.A.: Argumentation-based agents that explain their decisions. In: 2019 8th Brazilian Conference on Intelligent Systems (BRACIS), pp. 467–472. IEEE (2019)
Sarwar, M., Ray, R., Banerjee, A.: A contrastive plan explanation framework for hybrid system models. ACM Trans. Embed. Comput. Syst. 22(2), 1–51 (2023)
Sreedharan, S., Srivastava, S., Kambhampati, S.: Using state abstractions to compute personalized contrastive explanations for AI agent behavior. Artif. Intell. 301, 103570 (2021)
Stange, S., Kopp, S.: Effects of a social robot’s self-explanations on how humans understand and evaluate its behavior. In: Proceedings of the 2020 ACM/IEEE International Conference on Human-Robot Interaction, pp. 619–627 (2020)
Stepin, I., Alonso, J.M., Catala, A., Pereira-Fariña, M.: A survey of contrastive and counterfactual explanation generation methods for explainable artificial intelligence. IEEE Access 9, 11974–12001 (2021)
Van Bouwel, J., Weber, E.: Remote causes, bad explanations? J. Theor. Soc. Behav. 32(4), 437–449 (2002)
Winikoff, M.: Debugging agent programs with “why?” questions (2017)
Wooldridge, M.: Reasoning About Rational Agents. MIT Press (2003)
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
Jasinski, H., Morveli-Espinoza, M., Tacla, C.A. (2023). Towards Generating P-Contrastive Explanations for Goal Selection in Extended-BDI Agents. In: Naldi, M.C., Bianchi, R.A.C. (eds) Intelligent Systems. BRACIS 2023. Lecture Notes in Computer Science(), vol 14195. Springer, Cham. https://doi.org/10.1007/978-3-031-45368-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-031-45368-7_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-45367-0
Online ISBN: 978-3-031-45368-7
eBook Packages: Computer ScienceComputer Science (R0)