Zijun Chen

collaborators

2 papers

cs.LG2026

Achieving $ε^{- 2}$ Dependence for Average-Reward Q-Learning with a New Contraction Principle

Zijun Chen, Zaiwei Chen, Nian Si +1

We present the convergence rates of synchronous and asynchronous Q-learning for average-reward Markov decision processes, where the absence of contraction poses a fundamental chall…

cs.LG2025

Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning

Zijun Chen, Shengbo Wang, Nian Si

Motivated by practical applications where stable long-term performance is critical-such as robotics, operations research, and healthcare-we study the problem of distributionally ro…

Achieving ε−2 Dependence for Average-Reward Q-Learning with a New Contraction Principle

Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning

Achieving $ε^{- 2}$ Dependence for Average-Reward Q-Learning with a New Contraction Principle