We consider discounted Markov decision processes (MDPs) with countably-infinite state spaces, finite action spaces, and unbounded rewards. Typical examples of such MDPs are inventory management and ...

WENZHUAN ZHANG, HONGJIE WEI, MAXIMUM LIKELIHOOD ESTIMATION FOR SIMPLEX DISTRIBUTION NONLINEAR MIXED MODELS VIA THE STOCHASTIC APPROXIMATION ALGORITHM, The Rocky Mountain Journal of Mathematics, Vol.