Abstractions in Causal Models and Game Structures

Sylvia S. Kerkhove, Natasha Alechina, Mehdi Dastani
Proceedings of the Fifth Conference on Causal Learning and Reasoning, PMLR 323:932-948, 2026.

Abstract

We investigate abstractions in causal and strategic models of multi-agent systems, exploiting the relationship between these models. The paper contains two main results. The first one demonstrates that abstraction in causal models is a faithful correspondent of abstraction in strategic models, i.e., for a given causal model, if we generate a corresponding strategic model and abstract this model, we will obtain the same model as when we abstract the causal model first and then generate its corresponding strategic model. The second result is that a causal dependency in an abstract (high-level) model entails a causal dependency in the original (low-level) model. This allows us to reason about causes in a simpler abstract model and derive conclusions about causality in the much larger low-level model. These results set the stage for studying and using abstractions of causal models in multi-agent settings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v323-kerkhove26a, title = {Abstractions in Causal Models and Game Structures}, author = {Kerkhove, Sylvia S. and Alechina, Natasha and Dastani, Mehdi}, booktitle = {Proceedings of the Fifth Conference on Causal Learning and Reasoning}, pages = {932--948}, year = {2026}, editor = {Mazaheri, Bijan and Hanson, Niels Richard}, volume = {323}, series = {Proceedings of Machine Learning Research}, month = {06--08 Apr}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v323/main/assets/kerkhove26a/kerkhove26a.pdf}, url = {https://proceedings.mlr.press/v323/kerkhove26a.html}, abstract = {We investigate abstractions in causal and strategic models of multi-agent systems, exploiting the relationship between these models. The paper contains two main results. The first one demonstrates that abstraction in causal models is a faithful correspondent of abstraction in strategic models, i.e., for a given causal model, if we generate a corresponding strategic model and abstract this model, we will obtain the same model as when we abstract the causal model first and then generate its corresponding strategic model. The second result is that a causal dependency in an abstract (high-level) model entails a causal dependency in the original (low-level) model. This allows us to reason about causes in a simpler abstract model and derive conclusions about causality in the much larger low-level model. These results set the stage for studying and using abstractions of causal models in multi-agent settings.} }
Endnote
%0 Conference Paper %T Abstractions in Causal Models and Game Structures %A Sylvia S. Kerkhove %A Natasha Alechina %A Mehdi Dastani %B Proceedings of the Fifth Conference on Causal Learning and Reasoning %C Proceedings of Machine Learning Research %D 2026 %E Bijan Mazaheri %E Niels Richard Hanson %F pmlr-v323-kerkhove26a %I PMLR %P 932--948 %U https://proceedings.mlr.press/v323/kerkhove26a.html %V 323 %X We investigate abstractions in causal and strategic models of multi-agent systems, exploiting the relationship between these models. The paper contains two main results. The first one demonstrates that abstraction in causal models is a faithful correspondent of abstraction in strategic models, i.e., for a given causal model, if we generate a corresponding strategic model and abstract this model, we will obtain the same model as when we abstract the causal model first and then generate its corresponding strategic model. The second result is that a causal dependency in an abstract (high-level) model entails a causal dependency in the original (low-level) model. This allows us to reason about causes in a simpler abstract model and derive conclusions about causality in the much larger low-level model. These results set the stage for studying and using abstractions of causal models in multi-agent settings.
APA
Kerkhove, S.S., Alechina, N. & Dastani, M.. (2026). Abstractions in Causal Models and Game Structures. Proceedings of the Fifth Conference on Causal Learning and Reasoning, in Proceedings of Machine Learning Research 323:932-948 Available from https://proceedings.mlr.press/v323/kerkhove26a.html.

Related Material