A Learning Automaton Network and it's Dynamics
Fei Qian, Fujiya Unno, Hironori Hirata · IEEJ Transactions on Electronics Information and Systems · 1991
The behavior of neural networks is often described in terms of competition and cooperation formation. Cooperativity in neural networks probably takes many forms. Some of them are surely represented in the mathematical models and computer simulations to which the cooperativity has been applied. This paper is an attempt to add another level of meaning to computational cooperativity by using an reinforcement learning network with generalized learning automata. The collection of learning automata in the team situation acts as self-interested agents that work toward improving their performance with respect to their individual preference ordering. In the global state space of the network, the case of partially synchronous stochastic process is considered. In this case, the existence of mean field is shown and a reinforcement learning algorithm which can make the dynamics on the average reinforcement trajectory is presented.