PROJECT TITLE :

Predicting Dominance Rankings for Score-Based Games

ABSTRACT:

Game competitions may involve different player roles and be score-based mostly rather than win/loss based mostly. This raises the difficulty of how best to draw opponents for matches in ongoing competitions, and how best to rank the players in every role. An example is the Ms Pac-Man versus Ghosts Competition that requires competitors to develop software controllers to require charge of the sport's protagonists: participants could develop software controllers for either or both Ms Pac-Man and therefore the team of 4 ghosts. During this paper, we have a tendency to compare two ranking schemes for win-loss games, Bayes Elo and Glicko. We convert the sport into one in all win-loss (“dominance”) by matching controllers of identical type against the identical opponent in an exceedingly series of try-wise comparisons. This implicitly creates a “answer concept” as to what a constitutes a sensible player. We tend to analyze how several games are needed below two popular ranking algorithms, Glicko and Bayes Elo, before one can infer the strength of the players, according to our proposed answer concept, while not performing an exhaustive analysis. We have a tendency to show that Glicko should be the strategy of selection for online score-based mostly game competitions.