＂A learning automaton represents an important and powerful tool in the area of reinforcement learning and aims at learning the optimal one that maximizes the probability of being rewarded out of a set of allowable systems, actions, alternatives, candidates, or designs by the interaction with a random environment. During a cycle, an automaton chooses an action and then receives a stochastic response that can be either a reward or penalty from the environment. The action probability vector of choosing the next action is then updated by employing this response. The ability of learning how to choose the optimal action endows learning automata with high adaptability to the environment, thus saving great expense and time to find the optimal one in various difficult stochastic environments.＂--