paper-with-me

홈 › Papers

Doubly Inhomogeneous Reinforcement Learning

2022-11-08 · Liyuan Hu, Mengbing Li, Chengchun Shi, Zhenke Wu, Piotr Fryzlewicz

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.

📄 PDF Abstract BibTeX arXiv:2211.03983

Code (1)

zaza0209/dirl 공식 구현

Tasks

Change Point DetectionClusteringDecision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)Sequential Decision Making

Similar Papers 제목 키워드 기반

Semi-Parametric Inference for Doubly Stochastic Spatial Point Processes: An Approximate Penalized Poisson Likelihood Approach

2023-06-11 · Si Cheng, Jon Wakefield, Ali Shojaie

Doubly-stochastic point processes model the occurrence of events over a spatial domain as an inhomogeneous Poisson process conditioned on the realization of a random intensity function. They are flexible tools for captur…

Point Processesvalid

Off-policy Evaluation in Doubly Inhomogeneous Environments

2023-06-14 · Zeyu Bian, Chengchun Shi, Zhengling Qi, Lan Wang

This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inho…

Offline RLOff-policy evaluationReinforcement Learning (RL)

Multi-Sensor Multi-Scan Radar Sensing of Multiple Extended Targets

2023-10-13 · Martin V. Vejling, Christophe A. N. Biscio, Petar Popovski

We propose an efficient solution to the state estimation problem in multi-scan multi-sensor multiple extended target sensing scenarios. We first model the measurement process by a doubly inhomogeneous-generalized shot no…

ClusteringState Estimation

Doubly Robust Off-Policy Actor-Critic Algorithms for Reinforcement Learning

2019-12-11 · Riashat Islam, Raihan Seraj, Samin Yeasar Arnob, Doina Precup

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the…

continuous-controlContinuous Controlreinforcement-learningReinforcement Learning+2

Structure-Aware Transformer Policy for Inhomogeneous Multi-Task Reinforcement Learning

2021-09-29 · ICLR 2022 4 · Sunghoon Hong, Deunsol Yoon, Kee-Eung Kim

Modular Reinforcement Learning, where the agent is assumed to be morphologically structured as a graph, for example composed of limbs and joints, aims to learn a policy that is transferable to a structurally similar but …

Multi-Task Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1