On the learning behaviors of variable-structure stochastic automaton in the general n-teacher environment

Learning behaviors of a stochastic automaton operating in a multiteacher environment are considered. As a generalized form of the L_R-I scheme, the GL_R-I scheme is proposed as a reinforcement scheme in a multiteacher environment. It is shown that the GL_R-I scheme is absolutely expedient and ϵ-optimal in the general n-teacher environment. Learning behaviors of the GL_R-I scheme are simulated by computer and the results indicate the effectiveness of the GL_R-I scheme.