Cooperativity in Networks of Pattern Recognizing Stochastic Learning Automata

A class of learning tasks is described that combines aspects of learning automaton tasks and supervised learning pattern-classification tasks. We call these associative reinforcement learning tasks. An algorithm is presented, called the associative reward-penalty, or A R−P , algorithm, for which a form of optimal performance has been proved. This algorithm simultaneously generalizes a class of stochastic learning automata and a class of supervised learning pattern-classification methods. Simulation results are presented that illustrate the associative reinforcement learning task and the performance of the the A R−P algorithm. Additional simulation results are presented showing how cooperative activity in networks of interconnected A R−P automata can olve difficult nonlinear associative learning problems.