Abstract
Agent explanation generation is the task of justifying the decisions of an agent after observing its behaviour. Much of the previous explanation generation approaches can theoretically do so, but assuming the availability of explanation generation modules, reliable observations, and deterministic execution of plans. However, in real-life settings, explanation generation modules are not readily available, unreliable observations are frequently encountered, and plans are non-deterministic. We seek in this work to address these challenges. This work presents a data-driven approach to mining and validating explanations (and specifically belief-based explanations) of agent actions. Our approach leverages the historical data associated with agent system execution, which describes action execution events and external events (represented as beliefs). We present an empirical evaluation, which suggests that our approach to mining and validating belief-based explanations can be practical.
A. Ghose-Passed away prior to the submission of the manuscript. This is one of the last contributions by Aditya Ghose.
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
Similar content being viewed by others
Notes
- 1.
We submit that goal-based explanations are also of great value to develop explainable agents, and we believe that an extension of the techniques presented in this work can address these but are outside the scope of the present work.
- 2.
One can leverage JACK capability methods to make belief set activities available at agent level [14]. This manipulation allows, in turn, to store of enabling beliefs based on the user-defined data structure.
- 3.
The source code for XPlaM Toolkit (including the code for the approach presented here) has been published online at https://github.com/dsl-uow/xplam.
- 4.
We published the datasets supporting the conclusions of this work online at https://www.kaggle.com/datasets/alelaimat/explainable-bdi-agents.
References
Anjomshoae, S., Najjar, A., Calvaresi, D., Främling, K.: Explainable agents and robots: results from a systematic literature review. In: 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019), Montreal, Canada, 13–17 May 2019, pp. 1078–1088. International Foundation for Autonomous Agents and Multiagent Systems (2019)
Kaptein, F., Broekens, J., Hindriks, K., Neerincx, M.: Personalised self-explanation by robots: the role of goals versus beliefs in robot-action explanation for children and adults. In: 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pp. 676–682. IEEE (2017)
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)
Abdulrahman, A., Richards, D., Bilgin, A.A.: Reason explanation for encouraging behaviour change intention. In: Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems, pp. 68–77 (2021)
Georgeff, M., Rao, A.: Modeling rational agents within a bdi-architecture. In: Proceedings of 2nd International Conference on Knowledge Representation and Reasoning (KR 1991), pp. 473–484. Morgan Kaufmann (1991)
Harbers, M., van den Bosch, K., Meyer, J.-J.C.: A study into preferred explanations of virtual agent behavior. In: Ruttkay, Z., Kipp, M., Nijholt, A., Vilhjálmsson, H.H. (eds.) IVA 2009. LNCS (LNAI), vol. 5773, pp. 132–145. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04380-2_17
Calvaresi, D., Mualla, Y., Najjar, A., Galland, S., Schumacher, M.: Explainable multi-agent systems through blockchain technology. In: Calvaresi, D., Najjar, A., Schumacher, M., Främling, K. (eds.) EXTRAAMAS 2019. LNCS (LNAI), vol. 11763, pp. 41–58. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30391-4_3
Verhagen, R.S., Neerincx, M.A., Tielman, M.L.: A two-dimensional explanation framework to classify AI as incomprehensible, interpretable, or understandable. In: Calvaresi, D., Najjar, A., Winikoff, M., Främling, K. (eds.) EXTRAAMAS 2021. LNCS (LNAI), vol. 12688, pp. 119–138. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-82017-6_8
Mualla, Y.: Explaining the behavior of remote robots to humans: an agent-based approach. PhD thesis, Université Bourgogne Franche-Comté (2020)
Winikoff, M.: Jack™ intelligent agents: an industrial strength platform. In: Bordini, R.H., Dastani, M., Dix, J., El Fallah Seghrouchni, A. (eds.) Multi-Agent Programming. MSASSO, vol. 15, pp. 175–193. Springer, Boston, MA (2005). https://doi.org/10.1007/0-387-26350-0_7
Abdulrahman, A., Richards, D., Ranjbartabar, H., Mascarenhas, S.: Belief-based agent explanations to encourage behaviour change. In: Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents, pp. 176–178 (2019)
Multi-engine aeroplane operations and training. Technical report, Civil Aviation Safety Authority (July 2007)
Bordini, R,H., Hübner, J.M., Wooldridge, M.: Programming multi-agent systems in AgentSpeak using Jason. John Wiley & Sons (2007)
Howden, N., Rönnquist, R., Hodgson, A., Lucas, A.: Jack intelligent agents-summary of an agent infrastructure. In: 5th International Conference on Autonomous Agents, vol. 6 (2001)
Ginsberg, M.L., Smith, D.E.: Reasoning about action i: a possible worlds approach. Artifi. intell. 35(2), 165–195 (1988)
Winslett, M.S.: Reasoning about action using a possible models approach, pp. 1425–1429. Department of Computer Science, University of Illinois at Urbana-Champaign (1988)
Maruster, L., Weijters, A.J.M.M.T., van der Aalst, W.M.P.W., van den Bosch, A.: Process mining: discovering direct successors in process logs. In: Lange, S., Satoh, K., Smith, C.H. (eds.) DS 2002. LNCS, vol. 2534, pp. 364–373. Springer, Heidelberg (2002). https://doi.org/10.1007/3-540-36182-0_37
Fournier-Viger, P., Faghihi, U., Nkambou, R., Nguifo, E.M.: Cmrules: mining sequential rules common to several sequences. Knowl.-Based Syst. 25(1), 63–76 (2012)
Alelaimat, A., Ghose, A., Dam, K.H.: Xplam: a toolkit for automating the acquisition of BDI agent-based digital twins of organizations. Comput. Industry 145, 103805 (2023)
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)
Sindlar, M.P., Dastani, M.M., Dignum, F., Meyer, J.-J.C.: Mental state abduction of BDI-based agents. In: Baldoni, M., Son, T.C., van Riemsdijk, M.B., Winikoff, M. (eds.) DALT 2008. LNCS (LNAI), vol. 5397, pp. 161–178. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-540-93920-7_11
Sindlar, M.P., Dastani, M.M., Dignum, F., Meyer, J.-J.C.: Explaining and predicting the behavior of BDI-based agents in role-playing games. In: Baldoni, M., Bentahar, J., van Riemsdijk, M.B., Lloyd, J. (eds.) DALT 2009. LNCS (LNAI), vol. 5948, pp. 174–191. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-11355-0_11
Sequeira, P., Gervasio, M.: Interestingness elements for explainable reinforcement learning: understanding agents’ capabilities and limitations. Artif. Intell. 288, 103367 (2020)
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
Alelaimat, A., Ghose, A., Dam, H.K. (2023). Mining and Validating Belief-Based Agent Explanations. In: Calvaresi, D., et al. Explainable and Transparent AI and Multi-Agent Systems. EXTRAAMAS 2023. Lecture Notes in Computer Science(), vol 14127. Springer, Cham. https://doi.org/10.1007/978-3-031-40878-6_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-40878-6_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-40877-9
Online ISBN: 978-3-031-40878-6
eBook Packages: Computer ScienceComputer Science (R0)