Strategy Generation with Cognitive Distance in Two-Player Games

In game theoretical approaches to multi-agent systems, a payoff matrix is often given a priori and used by agents in action selection. By contrast, in this paper we approach the problem of decision making by use of the concept of cognitive distance, which is a notion of the difficulty of an action perceived subjectively by the agent. As opposed to ordinary physical distance, cognitive distance depends on the situation and skills of the agent, ultimately representing the perceived difficulty in performing an action given the current state. The concept of cognitive distance is applied to a two-player game scenario, and it is shown how an agent can learn a model of its skills by estimating and observing the outcomes of its actions. This skill model is then used during play in a minimax search for the best actions