Towards Cognitively Plausible Game Playing Systems

We propose to return to the roots of Artificial/ Computational Intelligence applicability to board games domain by attempting to mimic human way of playing (or human intelligence in a broader perspective). The paper provides the argumentation for potential virtues of developing cognitively-plausible pattern-based human-like playing systems. Such systems, besides playing games, may in principle, also be applied to other domains related to general problem-solving. In order to support theoretical considerations a cognitively-inspired game-playing framework is presented, "which is not focused on applying explicitly defined numerical evaluation function or performing extensive search, but instead takes advantage of context-based pattern templates and knowledge generalization techniques in a way that, to some extent, is alike to that of human players. Experimental evaluation of proposed approach in Connect Four proved its potential, "which also gives hope for successful application of the method to other, more demanding board games (e.g., chess or checkers). Certainly, reaching the level of play exhibited by the state of-the-art programs in the above-mentioned games, if at all attainable, would require substantial time and effort, but as advocated in the paper, this research avenue seems to be worth exploring.