Structural Causal Bandits under Markov Equivalence

Min Woo Park; Andy Arditi; Elias Bareinboim; Sanghack Lee

NeurIPS 2025poster0 citations

Structural Causal Bandits under Markov Equivalence

Min Woo Park, Andy Arditi, Elias Bareinboim, Sanghack Lee

Abstract

In decision-making processes, an intelligent agent with causal knowledge can optimize action spaces to avoid unnecessary exploration. A *structural causal bandit* framework provides guidance on how to prune actions that are unable to maximize reward by leveraging prior knowledge of the underlying causal structure among actions. A key assumption of this framework is that the agent has access to a fully-specified causal diagram representing the target system. In this paper, we extend the structural causal bandits to scenarios where the agent leverages a Markov equivalence class. In such cases, the causal structure is provided to the agent in the form of a *partial ancestral graph* (PAG). We propose a generalized framework for identifying potentially optimal actions within this graph structure, thereby broadening the applicability of structural causal bandits.

causal inferencestructural causal banditsmarkov equivalencepartial ancestral graphmaximal ancestral graph

BibTeX

@inproceedings{
park2025structural,
title={Structural Causal Bandits under Markov Equivalence},
author={Min Woo Park and Andy Arditi and Elias Bareinboim and Sanghack Lee},
booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
year={2025},
url={https://openreview.net/forum?id=3aFwsZxM5H}
}