ABSTRACT
This chapter deals with the learning methods based on Stochastic Learning Automata (SLA). The basic block structure of a SLA was explained along with the standard learning algorithms. The manner in which the automaton uses the response from the environment to select its next action is determined by the specific learning algorithm used. A SLA comprises two main building blocks: A Stochastic Automaton with a finite number of actions and a Random environment with which the automaton interacts; The Learning Algorithms by which the automata learns the optimal action. The relative reward strength algorithms were proposed by Rahul Simha and James F. Kurose. The automaton in this scheme operates in an S-Model environment but maintains and uses the most obtained reward for each action until that action is selected again. All the learning algorithms that have been assume a P-Model environment providing a binary response of success or failure.
