Proceedings

Unintended Consequences: Updating Causal Models

Joseph Y. Halpern, Evan Piermont, Marie-Louise Vierø

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 3872-3880.

https://doi.org/10.24963/ijcai.2026/431

Keywords

  • Knowledge Representation and Reasoning: Belief change
  • Knowledge Representation and Reasoning: Causality
  • Knowledge Representation and Reasoning: Reasoning about actions

Abstract

We examine how causal beliefs affect an agent's choices and how feedback on those choices leads to updated causal beliefs. Building on the structural-equations framework for modeling causality, we first examine the general problem of updating causal beliefs in the face of novel (and possibly inexplicable) data. We model an agent who is uncertain of the true causal model, and therefore entertains a probabilistic belief over the set of possible models. We then consider how causal beliefs influence choices by building a model of agency and utility on top of the usual structural-equations framework. Using these two components, we propose a notion of steady state, where the feedback received from an agent's optimal action, given her current beliefs about the true causal model, can be rationalized by those beliefs.

Joseph Y. Halpern, Evan Piermont, and Marie-Louise Vierø. 2026. Unintended Consequences: Updating Causal Models. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 3872–3880. https://doi.org/10.24963/ijcai.2026/431
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards