3 papers
cs.LG2026
Central Limit Theorems for Asynchronous Averaged Q-Learning
Xingtu Liu
This paper establishes central limit theorems for Polyak-Ruppert averaged Q-learning under asynchronous updates. We prove a non-asymptotic central limit theorem, where the converge…
cs.LG2026
An Information-Theoretic Analysis of OOD Generalization in Meta-Reinforcement Learning
Xingtu Liu
In this work, we study out-of-distribution (OOD) generalization in meta-reinforcement learning from an information-theoretic perspective. We begin by establishing OOD generalizatio…
cs.LG2025
Sample Complexity Bounds for Linear Constrained MDPs with a Generative Model
Xingtu Liu, Lin F. Yang, Sharan Vaswani
We consider infinite-horizon -discounted (linear) constrained Markov decision processes (CMDPs) where the objective is to find a policy that maximizes the expected cumulative r…