Clustering and Classification of Time Series in Real-Time Strategy Games - A machine learning approach for mapping StarCraft II games to clusters of game state time series while limited by fog of war

Detta är en Kandidat-uppsats från Göteborgs universitet/Institutionen för data- och informationsteknik

Sammanfattning: Real-time strategy (RTS) games feature vast action spaces and incomplete information,thus requiring lengthy training times for AI-agents to master them at the level of ahuman expert. Based on the inherent complexity and the strategical interplay betweenthe players of an RTS game, it is hypothesized that data sets of played games exhibitclustering properties as a result of the actions made by the players. These clusterscould potentially be used to optimize the training process of AI-agents, and gainunbiased insight into the gameplay dynamics. In this thesis, a method is presented todiscern such clusters and classify an ongoing game according to which of these clustersit most closely resembles, limited to the perspective of a single player. Six distinctclusters have been found in StarCraft II using hierarchical clustering over time, allof which depend on different combinations of game pieces and the timing of theiracquisitions in the game. An ongoing game can be classified, using neural networksand random forests, as a member of some cluster with accuracies ranging from 83%to 96% depending on the amount of information provided.

  HÄR KAN DU HÄMTA UPPSATSEN I FULLTEXT. (följ länken till nästa sida)