Abstract
We propose a framework for learning dependencies between variables in an environment with causal relations. We assume that the environment is fully observable and that the underlying causal structure is of a simple nature. We adapt the frameworks of the (epistemic) causal models from [4, 17], and propose a model inspired by action learning [6, 7]. We present two learning methods, using formal and algorithmic approaches. Our learning agents infer dependencies (atomic formulas of Dependence Logic) from observations of interventions on valuations (propositional states), and by doing so efficiently, they obtain insights into how to manipulate their surroundings to achieve goals.
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.
Here ‘\(\cdot \)’ stands for concatenation of sequences.
- 2.
Note that the same result is obtained by the learner for any sound and complete stream for the causal frame of this particular domain.
References
Baltag, A., van Benthem, J.: A simple logic of functional dependence. J. Philos. Log. 50(5), 939–1005 (2021). https://doi.org/10.1007/s10992-020-09588-z
Baltag, A., Gierasimczuk, N., Özgün, A., Vargas Sandoval, A.L., Smets, S.: A dynamic logic for learning theory. J. Log. Algebraic Methods Program. 109, 100485 (2019). https://doi.org/10.1016/j.jlamp.2019.100485
Barbero, F., Sandu, G.: Team semantics for interventionist counterfactuals: observations vs. interventions. J. Philos. Log. 50(3), 471–521 (2021). https://doi.org/10.1007/s10992-020-09573-6
Barbero, F., Schulz, K., Smets, S., Velázquez-Quesada, F.R., Xie, K.: Thinking about causation: a causal language with epistemic operators. In: Martins, M.A., Sedlár, I. (eds.) DaLi 2020. LNCS, vol. 12569, pp. 17–32. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-65840-3_2
Bolander, T., Gierasimczuk, N., Liberman, A.: Learning to act and observe in partially observable domains. In: Bezhanishvili, N., Yang, F. (eds.) Outstanding Contributions to Logic: Dick de Jongh. Springer, Cham (2023). (in preparation). https://doi.org/10.48550/arXiv.2109.06076
Bolander, T., Gierasimczuk, N.: Learning actions models: qualitative approach. In: van der Hoek, W., Holliday, W.H., Wang, W. (eds.) LORI 2015. LNCS, vol. 9394, pp. 40–52. Springer, Heidelberg (2015). https://doi.org/10.1007/978-3-662-48561-3_4
Bolander, T., Gierasimczuk, N.: Learning to act: qualitative learning of deterministic action models. J. Log. Comput. 28(2), 337–365 (2017). https://doi.org/10.1093/logcom/exx036
Dégremont, C., Gierasimczuk, N.: Finite identification from the viewpoint of epistemic update. Inf. Comput. 209(3), 383–396 (2011). https://doi.org/10.1016/j.ic.2010.08.002
Gierasimczuk, N.: Inductive inference and epistemic modal logic. In: Klin, B., Pimentel, E. (eds.) 31st EACSL Annual Conference on Computer Science Logic (CSL 2023). Leibniz International Proceedings in Informatics (LIPIcs), vol. 252, pp. 2:1–2:16. Schloss Dagstuhl - Leibniz-Zentrum für Informatik, Dagstuhl (2023). https://doi.org/10.4230/LIPIcs.CSL.2023.2
Gierasimczuk, N., Jonghde Jongh, D.: On the complexity of conclusive update. Comput. J. 56(3), 365–377 (2013). https://doi.org/10.1093/comjnl/bxs059
Glymour, C., Zhang, K., Spirtes, P.: Review of causal discovery methods based on graphical models. Front. Genet. 10, 524 (2019). https://doi.org/10.3389/fgene.2019.00524
Gold, M.: Language identification in the limit. Inf. Control 10(5), 447–474 (1967). https://doi.org/10.1016/S0019-9958(67)91165-5
Halpern, J.Y.: Actual Causality. The MIT Press, Cambridge (2016). https://doi.org/10.7551/mitpress/10809.001.0001
Hintikka, J., Sandu, G.: Informational independence as a semantical phenomenon. In: Fenstad, J.E., Frolov, I.T., Hilpinen, R. (eds.) Logic, Methodology and Philosophy of Science VIII, Studies in Logic and the Foundations of Mathematics, vol. 126, pp. 571–589. Elsevier (1989). https://doi.org/10.1016/S0049-237X(08)70066-1
McCormack, T., Bramley, N., Frosch, C., Patrick, F., Lagnado, D.: Children’s use of interventions to learn causal structure. J. Exp. Child Psychol. 141, 1–22 (2016). https://doi.org/10.1016/j.jecp.2015.06.017
Muentener, P., Bonawitz, E.: The development of causal reasoning. In: Waldmann, M.R. (ed.) The Oxford Handbook of Causal Reasoning, pp. 677–698. Oxford University Press (2017). https://doi.org/10.1093/oxfordhb/9780199399550.001.0001
Pearl, J.: Introduction to Probabilities, Graphs, and Causal Models, 2 edn., pp. 1–40. Cambridge University Press (2009). https://doi.org/10.1017/CBO9780511803161.003
Pearl, J., Mackenzie, D.: The Book of Why: The New Science of Cause and Effect, 1st edn. Basic Books Inc., USA (2018). https://doi.org/10.1007/s00146-020-00971-7
Peters, J.M., Janzing, D., Schölkopf, B.: Elements of Causal Inference: Foundations and Learning Algorithms: Foundations and Learning Algorithms. MIT Press, Cambridge (2017)
Väänänen, J.: Dependence Logic: A New Approach to Independence Friendly Logic (London Mathematical Society Student Texts). Cambridge University Press, Cambridge (2007). https://doi.org/10.1017/CBO9780511611193
Von Wright, G.: On the logic and epistemology of the causal relation. In: Suppes, P., Henkin, L., Joja, A., Moisil, G.C. (eds.) Proceedings of the Fourth International Congress for Logic, Methodology and Philosophy of Science, Bucharest, 1971. Studies in Logic and the Foundations of Mathematics, vol. 74, pp. 293–312. Elsevier (1973). https://doi.org/10.1016/S0049-237X(09)70366-0
Yang, F., Väänänen, J.: Propositional logics of dependence. Ann. Pure Appl. Log. 167(7), 557–589 (2016). https://doi.org/10.1016/j.apal.2016.03.003
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Thoft, K.B.P., Gierasimczuk, N. (2024). Learning by Intervention in Simple Causal Domains. In: Gierasimczuk, N., Velázquez-Quesada, F.R. (eds) Dynamic Logic. New Trends and Applications. DaLí 2023. Lecture Notes in Computer Science, vol 14401. Springer, Cham. https://doi.org/10.1007/978-3-031-51777-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-51777-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-51776-1
Online ISBN: 978-3-031-51777-8
eBook Packages: Computer ScienceComputer Science (R0)