Continuous and Discretized Generalized Pursuit Learning Schemes

A Learning Automaton is an automaton that interacts with a random environment, having as its goal the task of learning the optimal action based on its acquired experience. Many learning automata have been proposed, with the class of Estimator Algorithms being among the fastest ones. Thathachar and Sastry [24], through the Pursuit Algorithm, introduced the concept of learning algorithms. Their algorithm pursues only the current estimated optimal action. If this action is not the one with the minimum penalty probability, this algorithm pursues a wrong action. In this paper, we argue that a Pursuit scheme that generalizes the traditional Pursuit algorithm by pursuing all the actions with higher reward estimates than the chosen action, minimizes the probability of pursuing a wrong action, and is a faster converging scheme. To attest this, in this paper we present two new generalized Pursuit algorithms and also present a quantitative comparison of their performance against the existing Pursuit algorithms.