Prelimit Coupling and Steady-State Convergence of Constant-Step-Size Nonsmooth Contractive Stochastic Approximation
Nonsmooth Learning Algorithms Behave Differently from Smooth Ones Many learning algorithms, including Q-learning, update their estimates through noisy recursive rules. When these updates use a constant step size and involve nonsmooth operators, their long-run behavior can be difficult to characterize: the iterates do...