collaborators

5 papers

math.OC2026

Wasserstein Policy Gradient for Entropy-Regularized Linear-Quadratic Control

Zhaoyu Zhu, Rui Gao, Shuang Li

Wasserstein policy gradient (WPG) updates state-conditional action laws by transport in the action space. We study entropy-regularized discounted linear-quadratic (LQ) control. A B…

cs.LG2026

Global Convergence of Wasserstein Policy Gradient for Entropy-Regularized Reinforcement Learning

Zhaoyu Zhu, Rui Gao, Shuang Li

Wasserstein policy gradient (WPG) is a policy optimization method for reinforcement learning (RL) that exploits the optimal-transport geometry of action distributions. For the entr…

cs.LG2026

Wasserstein Proximal Policy Gradient

Zhaoyu Zhu, Shuhan Zhang, Rui Gao +1

We study policy gradient methods for continuous-action, entropy-regularized reinforcement learning through the lens of Wasserstein geometry. Starting from a Wasserstein proximal up…

math.OC2025

Historical Information Accelerates Decentralized Optimization: A Proximal Bundle Method

Zhao Zhu, Yu-Ping Tian, Xuyang Wu

Historical information, such as past function values or gradients, has significant potential to enhance decentralized optimization methods for two key reasons: first, it provides r…

cs.LG2025

Elucidating Rectified Flow with Deterministic Sampler: Polynomial Discretization Complexity for Multi and One-step Models

Ruofeng Yang, Zhaoyu Zhu, Bo Jiang +2

Recently, rectified flow (RF)-based models have achieved state-of-the-art performance in many areas for both the multi-step and one-step generation. However, only a few theoretical…