This work concerns controlled Markov chains with denumerable state space, (possibly) unbounded cost function, and an expected average cost criterion. Under a Lyapunov function condition, together with mild continuity-compactness assumptions, a simple necessary and sufficient criterion is given so that the relative value functions and differential costs produced by the value iteration scheme converge pointwise to the solution of the optimality equation; this criterion is applied to obtain convergence results when the cost function is bounded below or bounded above.

We consider the adaptive control of Markov chains under the weak accessibility condition with a view to minimizing the learning loss. A certainty equivalence control with a forcing scheme is constructed. We use a stationary randomized control scheme for forcing and compute a maximum likelihood estimate of the unknown parameter from the resulting observations. We obtain an exponential upper bound on the rate of decay of the probability of error. This allows us to choose the rate of forcing appropriately, whereby we achieve a o(f(n) log n) learning loss for any function as .

The problem studied is that of controlling a finite Markov chain so as to maximize the long-run expected reward per unit time. The chain's transition probabilities depend upon an unknown parameter taking values in a subset [a, b] of Rn. A control policy is defined as the probability of selecting a control action for each state of the chain. Derived is a Taylor-like expansion formula for the expected reward in terms of policy variations. Based on that result, a recursive stochastic gradient algorithm is presented for the adaptation of the control policy at consecutive times. The gradient depends on the estimated transition parameter which is also recursively updated using the gradient of the likelihood function. Convergence with probability 1 is proved for the control and estimation algorithms.

We consider a finite controlled Markov chain, the description of which depends on an unknown parameter a, and investigate the following control policy. To each a an optimal stationary control is associated. a is estimated recurrently from the trajectory by the minimum contrast method, and the optimal stationary control corresponding to the estimate is used. We present asymptotic properties of the estimate and of the criterion function. They follow from the law of large numbers and from the central limit theorem for controlled Markov chains derived with the aid of martingales.