7 papers
Convergence and Regret of the Policy Gradient for Multi-Armed Bandits in Diffusion Environment
Yanwei Jia, Du Ouyang
This paper studies the policy gradient update for a multi-arm bandit problem in diffusion environment that is described by a stochastic differential equation (SDE) under the contin…
A Zeroth-Order Deep Learning Method for Fully Nonlinear Parabolic Partial Differential Equations with Unknown Coefficients
Yanwei Jia, Du Ouyang, Huyên Pham +1
High-dimensional partial differential equations (PDEs) with unknown coefficients arise widely in scientific machine learning, including continuous-time reinforcement learning, yet…
Quasi-Monte Carlo for SDE Simulation: Error Analysis and Dimensionality Reduction
Du Ouyang, Zexin Pan, Zhijian He
We investigate the numerical simulation of general stochastic differential equations (SDEs) using Quasi-Monte Carlo (QMC) methods. First, we provide a rigorous theoretical analysis…
Switched Linear Ensemble Systems and Structural Controllability
Haoyu Yin, Yi Li, Ouyang Du +2
This paper introduces and solves a structural controllability problem for ensembles of switched linear systems. All individual systems in the ensemble are sparse and governed by th…
Uncertainty quantification using importance-sampled quasi-Monte Carlo with dimension-independent convergence rates
Zexin Pan, Du Ouyang, Zhijian He
Quasi-Monte Carlo (QMC) integration over unbounded domains remains challenging due to the high dimensionality of sampling space and the boundary growth of the integr…
Accuracy of Discretely Sampled Stochastic Policies in Continuous-time Reinforcement Learning
Yanwei Jia, Du Ouyang, Yufei Zhang
Stochastic policies (also known as relaxed controls) are widely used in continuous-time reinforcement learning algorithms. However, executing a stochastic policy and evaluating its…