Structural Causal Bandits under Markov Equivalence

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

Keywords: causal inference, structural causal bandits, markov equivalence, partial ancestral graph, maximal ancestral graph

TL;DR: We study the graphical characterization of structural causal bandits framework under Markov equivalence class.

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.

Primary Area: Probabilistic methods (e.g., variational inference, causal inference, Gaussian processes)

Submission Number: 26106