Discretized estimator learning automata

The improvements gained by rendering the various estimator learning algorithms discrete are investigated. This is done by restricting the probability of selecting an action to a finite discrete subset of [0, 1]. This modification is proven to be ε-optimal in all stationary environments. Various discretized estimator algorithms (DEAs) are constructed. Subsequently, members of the family of DEAs are shown to be ε-optimal by deriving two sufficient conditions required for the ε-optimality-the properties of monotonicity and moderation. A conjecture about the necessity of these conditions for ε-optimality is presented. Experimental results indicate that the discrete modifications improve the performance of the algorithms so that the automata constitute fast-converging and accurate learning automata