A generalized learning algorithm for an automaton operating in a multiteacher environment
Abtin Ansari, George P. Papavassilopoulos · IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics) · 1999
Learning algorithms for an automaton operating in a multiteacher environment are considered. These algorithms are classified based on the number of actions given as inputs to the environments and the number of responses (outputs) obtained from the environments. In this paper, we present a general class of learning algorithm for multi-input multi-output (MIMO) models. We show that the proposed learning algorithm is absolutely expedient and epsilon-optimal in the sense of average penalty. The proposed learning algorithm is a generalization of Baba's GAE algorithm and has applications in solving, in a parallel manner, multi-objective optimization problems in which each objective function is disturbed by noise.