Lei Ying

collaborators

4 papers

math.PR2026

Steady-State Approximation Error of Heterogeneous Mean-Field Models

Lei Ying

This paper studies heterogeneous mean-field models in which agent parameters are sampled from a population distribution. We establish an $O (1/ M)$ bound on the steady-state mean-squ…

cs.LG2026

On the Global Convergence of Risk-Averse Natural Policy Gradient Methods with Expected Conditional Risk Measures

Xian Yu, Lei Ying

Risk-sensitive reinforcement learning (RL) has become a popular tool for controlling the risk of uncertain outcomes and ensuring reliable performance in highly stochastic sequentia…

math.OC2025

Achieving $O ~ (1/ N)$ Optimality Gap in Restless Bandits through Gaussian Approximation

Chen Yan, Weina Wang, Lei Ying

We study the finite-horizon Restless Multi-Armed Bandit (RMAB) problem with $N$ homogeneous arms. Prior work has shown that when an RMAB satisfies a non-degeneracy condition, Linea…

cs.LG2025

Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence

Minheng Xiao, Xian Yu, Lei Ying

Risk-sensitive reinforcement learning (RL) is crucial for maintaining reliable performance in high-stakes applications. While traditional RL methods aim to learn a point estimate o…

Steady-State Approximation Error of Heterogeneous Mean-Field Models

On the Global Convergence of Risk-Averse Natural Policy Gradient Methods with Expected Conditional Risk Measures

Achieving O~(1/N) Optimality Gap in Restless Bandits through Gaussian Approximation

Policy Gradient Methods for Risk-Sensitive Distributional Reinforcement Learning with Provable Convergence

Achieving $O ~ (1/ N)$ Optimality Gap in Restless Bandits through Gaussian Approximation