Doubly Inhomogeneous Reinforcement Learning
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 17 of its 46 references that are in the map. First posted on arXiv 8 Nov 2022.
Builds on
17 of 46 references.
References · 17
- 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 265
- 2021Non-stationary Reinforcement Learning without Prior Knowledge: An Optimal Black-box Approachcited by 98
- 2020Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimismcited by 76
- 2019Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activitycited by 70
- 2020Batch Policy Learning in Average Reward Markov Decision Processescited by 69
- 2016Estimating Dynamic Treatment Regimes in Mobile Health Using V-learningcited by 65
- 2020Statistical Inference of the Value Function for Reinforcement Learning in Infinite Horizon Settingscited by 65
- 2019Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended versioncited by 36
- 2020Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Makingcited by 30
- 2018Dynamic Assortment Optimization with Changing Contextual Informationcited by 28
- 2021Online Bootstrap Inference For Policy Evaluation in Reinforcement Learningcited by 26
- 2021Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learningcited by 26
5 more
- 2021Optimistic Policy Optimization is Provably Efficient in Non-stationary MDPscited by 16
- 2022Testing Stationarity and Change Point Detection in Reinforcement Learningcited by 12
- 2020Personalized Policy Learning using Longitudinal Mobile Health Datacited by 10
- 2022Reinforcement Learning with Heterogeneous Data: Estimation and Inferencecited by 7
- 2021Pattern Transfer Learning for Reinforcement Learning in Order Dispatchingcited by 4
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 2.
3 papers.