Sharp Statistical Rates for Asynchronous TD Learning with Markovian Data

arXiv:2609.38880 · stat.ML, cs.LG · Submitted 2026-09-30 · Read on arXiv

stat.ML, cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Accuracy — 10× in this paper · explained in 1 episode
• Q-learning — 5× in this paper · explained in 3 episodes
• Reward Function — 5× in this paper · explained in 2 episodes
• Adaptive Selection — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Error Decomposition — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Minimax optimality — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Sample Complexity — 1× in this paper · explained in 15 episodes

Sources

• Concentration of General Stochastic Approximation Under Heavy-Tailed Markovian Noise
• Bias and Extrapolation in Markovian Linear Stochastic Approximation with Constant Stepsizes
• A Finite-Iteration Theory for Asynchronous Categorical Distributional Temporal-Difference Learning
• A Single Stepsize Suffices for Unprojected Linear TD(0): Simultaneous Robust and Fast Rates via Polyak--Ruppert Averaging
• Is Q-Learning Minimax Optimal? A Tight Sample Complexity Analysis

Related papers

• Behavior of prediction performance metrics with rare events
• Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
• A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
• One Permutation Is All You Need: Fast, Deterministic Feature Importance and Model Stress-Testing
• Online Conformal Prediction for Non-Exchangeable Panel Data
• Deep Time-Series Forecasting in 10 Years: A Survey