Establishes last-iterate convergence rates for on-policy Q-learning under minimal irreducibility assumptions, with sample complexity O(1/ξ²) matching off-policy up to exploration factors.
Mehdi and Crump, Trafford and Far, Behrouz , title =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2verdicts
UNVERDICTED 2representative citing papers
Vanishing L2 regularization yields provable convergence for softmax MAB policies and improves empirical performance.
citing papers explorer
-
A Minimal-Assumption Analysis of Q-Learning with Time-Varying Policies
Establishes last-iterate convergence rates for on-policy Q-learning under minimal irreducibility assumptions, with sample complexity O(1/ξ²) matching off-policy up to exploration factors.
-
Vanishing L2 regularization for the softmax Multi Armed Bandit
Vanishing L2 regularization yields provable convergence for softmax MAB policies and improves empirical performance.