A Novel way of Training a Neural Network with Reinforcement learning and without Back Propagation

This paper introduces, explores and shows a new way to optimize the weights of a neural network. This new technique does not use back propagation or relies on gradient descent. The core idea is to combine both Game Theory and Reinforcement Learning to train a Neural network. We structure a game of learning automata agents, specifically Continuous Action Learning Automata (CALA) agents, that iteratively converges to a global minimum. Each CALA agent is associated with a weight in a neural network, and when the game converges to a global minimum, we can say that the neural network has been trained. By using a game of CALA agents we can deal with input that has been corrupted by noise, do not have to worry about the vanishing gradient problem or worry about over fitting and is structured better for parallel computing.