Abstract
Research on general machine intelligence is concerned with building machines that are capable of performing a multitude of highly complex tasks in environments as complex as the real world. A system placed in such a world of indefinite possibilities and never-ending novelty must be able to adjust its plans dynamically to adapt to changes in the environment. These adjustments, however, should be based on an informed explanation that describes the hows and whys of interventions necessary to reach a goal. This means that explanations are at the core of planning in a self-explaining way. Using Assumption-Based Argumentation we present a way how an AGI-aspiring system could generate meaningful explanations. These explanations consist of argumentation graphs that represent proponents (i.e., solutions to the task) and opponents (contradictions to these solutions). They thus provide information on why which intervention is necessary, thus making an informed commitment to a particular action possible. Additionally, we show how such argumentation graphs could be used dynamically to adjust plans when contradicting evidence is observed from the environment.
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.
- 2.
Something that is necessary when a system learns from experience and can therefore never know whether existing knowledge is correct - in short, when it is non-axiomatic.
- 3.
A purely forward-chaining system would immediately run into problems of computational explosion since the possible number of interventions with the real world is infinite (or at least extremely large).
- 4.
For a more detailed analysis of how noise and uncertainty can be handled in such a reasoning system, we refer the reader to [5].
- 5.
Described in [13], available on GitHub at https://github.com/robertcraven/abagraph—accessed 25th of April 2024.
- 6.
Code accessible on GitHub: https://github.com/IIIM-IS/AERA_Visualizer—accessed 25th of April 2024.
References
Belenchia, M., Thórisson, K.R., Eberding, L.M., Sheikhlar, A.: Elements of task theory. In: Goertzel, B., Iklé, M., Potapov, A. (eds.) AGI 2021. LNCS (LNAI), vol. 13154, pp. 19–29. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-93758-4_3
Bondarenko, A., Dung, P.M., Kowalski, R.A., Toni, F.: An abstract, argumentation-theoretic approach to default reasoning. Artif. Intell. 93(1–2), 63–101 (1997)
Bondarenko, A., Toni, F., Kowalski, R.A.: An assumption-based framework for non-monotonic reasoning (1993)
Dung, P.M., Kowalski, R.A., Toni, F.: Assumption-based argumentation. Argum. Artif. Intell. 199–218 (2009)
Eberding, L.M., Thórisson, K.R.: Causal reasoning over probabilistic uncertainty. In: Hammer, P., Alirezaie, M., Strannegard, C. (eds.) AGI 2023. LNCS, vol. 13921, pp. 74–84. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-33469-6_8
Li, Y.: Deep reinforcement learning: an overview. arXiv preprint arXiv:1701.07274 (2017)
Linardatos, P., Papastefanopoulos, V., Kotsiantis, S.: Explainable AI: a review of machine learning interpretability methods. Entropy 23(1), 18 (2020)
Nivel, E., Thórisson, K.R.: Towards a programming paradigm for control systems with high levels of existential autonomy. In: Kühnberger, K.-U., Rudolph, S., Wang, P. (eds.) AGI 2013. LNCS (LNAI), vol. 7999, pp. 78–87. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-39521-5_9
Nivel, E., et al.: Bounded recursive self-improvement. RUTR 13006 (2013)
Thompson, J., Thórisson, K.R.: ABA argument graphs with constraints. In: International Conference on Computational Models of Argument (2024, in press)
Thórisson, K.R.: The ‘explanation hypothesis’ in general self-supervised Learning. Proc. Mach. Learn. Res. 159, 5–27 (2021)
Thórisson, K.R., Rörbeck, H., Thompson, J., Latapie, H.: Explicit goal-driven autonomous self-explanation generation. In: Hammer, P., Alirezaie, M., Strannegard, C. (eds.) AGI 2023. LNCS, vol. 13921, pp. 286–295. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-33469-6_29
Toni, F., Craven, R.: Argument graphs and assumption-based argumentation (2016)
Walton, D.: Argumentation theory: a very short introduction. In: Simari, G., Rahwan, I. (eds.) Argumentation in Artificial Intelligence, pp. 1–22. Springer, Boston (2009). https://doi.org/10.1007/978-0-387-98197-0_1
Acknowledgments
This work was funded in part by the Icelandic Research Fund (IRF) (grant number 228604-051) and a research grant from Cisco Systems, USA. The authors would like to thank the rest of the GMI research team at CADIA, Reykjavik U., for extensive discussions on the topics of this paper.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
Disclosure of Interests
The authors have no competing interests to declare.
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Eberding, L.M., Thompson, J., Thórisson, K.R. (2024). Argument-Driven Planning and Autonomous Explanation Generation. In: Thórisson, K.R., Isaev, P., Sheikhlar, A. (eds) Artificial General Intelligence. AGI 2024. Lecture Notes in Computer Science(), vol 14951. Springer, Cham. https://doi.org/10.1007/978-3-031-65572-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-65572-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-65571-5
Online ISBN: 978-3-031-65572-2
eBook Packages: Computer ScienceComputer Science (R0)