Use of neural networks as decision makers in strategic situations

Intelligence consists of the ability to make right decisions in a given situation in order to achieve a certain goal. Game Theory provides mathematical models of real-world situations for studying intelligent behavior. Most of time, effective decision-making in strategic situations (such as competitive situations) requires nonlinear mapping between stimulus and response. This sort of mapping can be provided by Artificial Neural Networks. This paper describes the use of a human-like Artificial Neural Network to find the optimal strategy in strategic situations without injecting expert knowledge. In order to train such a Neural Network, an unsupervised reinforcement-learning rule using Back-Propagation is introduced. Unlike most of reinforcement learning systems, this learning rule can operate with continuous outputs, what makes it worth for a lot of different applications. Finally, this decision maker is used to find the optimal strategy in the well-known Iterated Prisoner's Dilemma, in order to demonstrate that this human-like Artificial Neural Networks can be used to design machines that are also capable of intelligent behavior.