Recent Advances in Causal Machine Learning and Dynamic Policy Learning

ABSTRACT Causal machine learning has emerged as a vital field at the intersection of machine learning and econometrics, addressing challenges in estimating treatment effect heterogeneity and optimizing policies. The first half of this review examines recent advances in causal machine learning within a static framework, covering methods such as meta‐learners, double machine learning, and causal forests, which improve conditional average treatment effect estimation and support personalized decision‐making. The second half focuses on dynamic policy learning, which integrates dynamic treatment regimes and reinforcement learning techniques to address sequential decision problems. We discuss value‐based, policy‐based, and model‐based approaches in both online and offline environments, and conclude with the challenges of offline settings, fundamentally a causal inference problem, together with strategies to address them. This article is categorized under: Statistical Learning and Exploratory Methods of the Data Sciences > Exploratory Data Analysis Statistical Learning and Exploratory Methods of the Data Sciences > Modeling Methods Statistical Learning and Exploratory Methods of the Data Sciences > Classification and Regression Trees