arXiv subjects

Lifeng Wei

Publications and source records attributed to Lifeng Wei.

3 recordsLinked to original sources

arXiv2025

Reinforcement Learning Framework For Stochastic Optimal Control Problem Under Model Uncertainty

We develop a continuous-time entropy-regularized reinforcement learning framework under model uncertainty. By applying Sion's minimax theorem, we transform the intractable robust control problem into an equivalent standard entropy-regularized stochastic control problem, facilitating reinforcement learning algorithms. We establish sufficient conditions for the theorem's validity and demonstrate our approach on linear-quadratic problems with uncertain model parameters following Bernoulli and uniform distributions.

math.OC↗

arXiv2020

Dynamic Programming Principle for Backward Doubly Stochastic Recursive Optimal Control Problem and Sobolev Weak Solution of The Stochastic Hamilton-Bellman Equation

In this paper, we study backward doubly stochastic recursive optimal control problem where the cost function is described by the solution of a backward doubly stochastic differential equation. We give the dynamical programming principle for this kind of optimal control problem and show that the value function is the unique Sobolev weak solution for the corresponding stochastic Hamilton-Jacobi-Bellman equation.

math.PR↗

arXiv2019

Unsupervised Object Segmentation with Explicit Localization Module

In this paper, we propose a novel architecture that iteratively discovers and segments out the objects of a scene based on the image reconstruction quality. Different from other approaches, our model uses an explicit localization module that localizes objects of the scene based on the pixel-level reconstruction qualities at each iteration, where simpler objects tend to be reconstructed better at earlier iterations and thus are segmented out first. We show that our localization module improves the quality of the segmentation, especially on a challenging background.

cs.CV↗