Abstract
A system deployed in the real world will need to handle uncertainty in its observations and interventions. For this, we present an approach to introduce uncertainty of state variables in causal reasoning using a constructivist AI architecture. Open questions of how noisy data can be handled and intervention uncertainty can be represented in a causal reasoning system will be addressed. In addition, we will show how handling uncertainty can improve a system’s planning and attention mechanisms. We present the reasoning process of the system, including reasoning over uncertainty, in the form of a feed-forward algorithm, highlighting how noisy data and beliefs of states can be included in the process of causal reasoning.
This work was funded in part by the Icelandic Research Fund (IRF) (grant number 228604-051) and a research grant from Cisco Systems, USA.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See https://openaera.org – accessed Apr. 6, 2023.
References
Eberding, L.M.: Comparison of machine learners on an ABA experiment format of the Cart-Pole Task. In: International Workshop on Self-Supervised Learning, pp. 49–63. PMLR (2022)
Eberding, L.M., Thórisson, K.R., Sheikhlar, A., Andrason, S.P.: SAGE: task-environment platform for evaluating a broad range of AI learners. In: Goertzel, B., Panov, A.I., Potapov, A., Yampolskiy, R. (eds.) AGI 2020. LNCS (LNAI), vol. 12177, pp. 72–82. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-52152-3_8
Goertzel, B., Iklé, M., Goertzel, I.F., Heljakka, A.: Probabilistic Logic Networks: A Comprehensive Framework for Uncertain Inference. Springer, New York (2008). https://doi.org/10.1007/978-0-387-76872-4
Hammer, P., Lofthouse, T.: ‘OpenNARS for applications’: architecture and control. In: Goertzel, B., Panov, A.I., Potapov, A., Yampolskiy, R. (eds.) AGI 2020. LNCS (LNAI), vol. 12177, pp. 193–204. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-52152-3_20
Nivel, E., et al.: Bounded recursive self-improvement. arXiv preprint arXiv:1312.6764 (2013)
Sheikhlar, A., Eberding, L.M., Thórisson, K.R.: Causal generalization in autonomous learning controllers. In: Goertzel, B., Iklé, M., Potapov, A. (eds.) AGI 2021. LNCS (LNAI), vol. 13154, pp. 228–238. Springer, Cham (2022). https://doi.org/10.1007/978-3-030-93758-4_24
Thórisson, K.R.: A new constructivist AI: from manual methods to self-constructive systems. In: Wang, P., Goertzel, B. (eds.) Theoretical Foundations of Artificial General Intelligence, pp. 145–171. Springer, Paris (2012). https://doi.org/10.2991/978-94-91216-62-6_9
Thórisson, K.R.: Machines with autonomy & general intelligence: which methodology? In: Proceedings of the Workshop on Architectures for Generality and Autonomy (2017)
Thórisson, K.R.: The ‘explanation hypothesis’ in general self-supervised learning. In: Proceedings of Machine Learning Research, vol. 159, pp. 5–27 (2021)
Thrun, S.: Probabilistic robotics. Commun. ACM 45(3), 52–57 (2002)
Wang, P.: Non-Axiomatic Reasoning System: Exploring the Essence of Intelligence. Indiana University (1995)
Wang, P.: Rigid Flexibility: The Logic of Intelligence, vol. 34. Springer, Dordrecht (2006)
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
Eberding, L.M., Thórisson, K.R. (2023). Causal Reasoning over Probabilistic Uncertainty. In: Hammer, P., Alirezaie, M., Strannegård, C. (eds) Artificial General Intelligence. AGI 2023. Lecture Notes in Computer Science(), vol 13921. Springer, Cham. https://doi.org/10.1007/978-3-031-33469-6_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-33469-6_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33468-9
Online ISBN: 978-3-031-33469-6
eBook Packages: Computer ScienceComputer Science (R0)