A Bayesian Network-based Uncertainty Modeling (BNUM) to Analyze and Predict Next Optimal Moves in Given Game Scenario

Abstract

As machine learning emerged, it is being used in a variety of applications like speech recognition, image recognition, sequence modeling, etc., Sequence modeling is one type of application where resultant sequences are generated based on historical data inputs provided. These sequences are fairly work in an uncertain environment like games or sports. In the case of a game or a sport, there is a sequence of moves selected by multiple players. There is a statistical uncertainty observed for simple to more complex games. For example, while playing chess, a simple statistical modeled uncertainty would be enough to choose the next possible. This move selection is dependent on available free spaces of pieces or pawns. The sports like tennis, cricket, and other games need a more complex design for uncertainty modeling for next move selection. A Bayesian Network model will work if there is fairly less uncertainty in the selection of the next move. A Bayesian Network-based model will be best fitted if all possible moves are included before training any machine learning or deep learning model. This will be achieved with the usage of the Context-Li model. The proposed Bayesian Network-based Uncertainty Modeling (BNUM) is used to incorporate uncertainty, for next move selection. BNUM is a multi-variable, multi-level association to incubate uncertainty in learning. It helps to predict the next move in an uncertain gaming environment. Different case studies are incorporated to verify the hypothesis and the results are a sequence of moves represented in the context graph.