Abstract-The fastest learning automata (LA) algorithms currently available fall in the family of estimator algorithms introduced by Thathachar and Sastry [24]. The pioneering work of these authors was the pursuit algorithm, which 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, we present two new generalized pursuit algorithms (GPAs) and also present a quantitative comparison of their performance against the existing pursuit algorithms. Empirically, the algorithms proposed here are among the fastest reported LA to date.Index Terms-Estimator algorithms, learning automata (LA), pursuit algorithms.

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 [23], through the Pursuit Algorithm, introduced the concept of learning algorithms that pursue the current optimal action, following a Reward-Penalty learning philosophy. Later, Oommen and Lanctôt [16] extended the Pursuit Algorithm into the discretized world by presenting the Discretized Pursuit Algorithm, based on a Reward-Inaction learning philosophy. In this paper, we argue that the Reward-Penalty and RewardInaction learning paradigms in conjunction with the continuous and discrete models of computation lead to four versions of Pursuit Learning Automata. We contend that a scheme that merges the Pursuit concept with the most recent response of the Environment permits the algorithm to utilize the LA's longterm and short-term perspectives of the Environment. In this paper, we present all the four resultant Pursuit algorithms, and also present a quantitative comparison between them. Although the present comparison is solely based on rigorous experimental results, we are currently investigating a formal convergence analysis of the various schemes.

No abstract

No abstract

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 [23], through the Pursuit Algorithm, introduced the concept of learning algorithms that pursue the current optimal action, following a Reward-Penalty learning philosophy. Later, Oommen and Lanctôt [16] extended the Pursuit Algorithm into the discretized world by presenting the Discretized Pursuit Algorithm, based on a Reward-Inaction learning philosophy. In this paper, we argue that the Reward-Penalty and RewardInaction learning paradigms in conjunction with the continuous and discrete models of computation lead to four versions of Pursuit Learning Automata. We contend that a scheme that merges the Pursuit concept with the most recent response of the Environment permits the algorithm to utilize the LA's longterm and short-term perspectives of the Environment. In this paper, we present all the four resultant Pursuit algorithms, and also present a quantitative comparison between them. Although the present comparison is solely based on rigorous experimental results, we are currently investigating a formal convergence analysis of the various schemes.