Learning Automata is inconvenient to describe algorithms as finite-state automata, so a move was made to describe the internal state of the agent as a probability distribution according to which actions would be chosen. The probabilities of taking different actions would be adjusted according to their previous successes and failures. Learning automata select their current action based on past experiences from the environment. It is an adaptive decision-making unit situated in a random environment that learns the optimal action through repeated interactions with its environment.
Learning Automata
