Establishes Õ(1/k) mean-square last-iterate convergence for asynchronous average-reward Q-learning with adaptive stepsizes and proves adaptivity is necessary.
Revisiting step-size assumptions in stochastic approximation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
Constant stepsize SA with decision-dependent Markovian noise has stationary bias O(alpha) under Poisson-Gateaux differentiability, plus finite-time moment bounds and weak convergence.
citing papers explorer
-
From Set Convergence to Pointwise Convergence: Finite-Time Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes
Establishes Õ(1/k) mean-square last-iterate convergence for asynchronous average-reward Q-learning with adaptive stepsizes and proves adaptivity is necessary.
-
Revisiting the Constant Stepsize Stochastic Approximation with Decision-Dependent Markovian Noise
Constant stepsize SA with decision-dependent Markovian noise has stationary bias O(alpha) under Poisson-Gateaux differentiability, plus finite-time moment bounds and weak convergence.