Doubly Inhomogeneous Reinforcement Learning

TL;DR

This paper introduces a novel reinforcement learning algorithm designed to handle environments with changing dynamics over time and across individuals, improving decision-making in non-stationary, heterogeneous settings.

Contribution

It proposes an original, robust method combining change point detection and clustering to identify stable data segments for better policy learning in doubly inhomogeneous environments.

Findings

Method effectively detects change points and clusters in complex environments.

Algorithm outperforms existing approaches in simulations.

Real data application demonstrates practical utility.

Abstract

This paper studies reinforcement learning (RL) in doubly inhomogeneous environments under temporal non-stationarity and subject heterogeneity. In a number of applications, it is commonplace to encounter datasets generated by system dynamics that may change over time and population, challenging high-quality sequential decision making. Nonetheless, most existing RL solutions require either temporal stationarity or subject homogeneity, which would result in sub-optimal policies if both assumptions were violated. To address both challenges simultaneously, we propose an original algorithm to determine the ``best data chunks" that display similar dynamics over time and across individuals for policy learning, which alternates between most recent change point detection and cluster identification. Our method is general, and works with a wide range of clustering and change point detection algorithms. It is multiply robust in the sense that it takes multiple initial estimators as input and only requires one of them to be consistent. Moreover, by borrowing information over time and population, it allows us to detect weaker signals and has better convergence properties when compared to applying the clustering algorithm per time or the change point detection algorithm per subject. Empirically, we demonstrate the usefulness of our method through extensive simulations and a real data application.