Authors:
Alper Kilic
;
Mehmet Akif Gunes
and
Sanem Sariel
Affiliation:
Istanbul Technical University, Turkey
Keyword(s):
Player Profiling, Hidden Markov Model, Sliding Window Method, the Vindinium Game.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Biomedical Engineering
;
Biomedical Signal Processing
;
Computational Intelligence
;
Data Manipulation
;
Data Mining
;
Databases and Information Systems Integration
;
Enterprise Information Systems
;
Evolutionary Computing
;
Health Engineering and Technology Applications
;
Human-Computer Interaction
;
Knowledge Discovery and Information Retrieval
;
Knowledge-Based Systems
;
Machine Learning
;
Methodologies and Methods
;
Neurocomputing
;
Neurotechnology, Electronics and Informatics
;
Pattern Recognition
;
Physiological Computing Systems
;
Sensor Networks
;
Signal Processing
;
Soft Computing
;
Symbolic Systems
Abstract:
In this paper, we present a player profiling system applicable for both human players and bots in video games. The Vindinium artificial intelligence (AI) contest is selected as the test-bed for analyzing the performance of our system. In this game, AI bots compete with each other in a systematically generated environment to achieve the highest score. Our profiling method is based on Hidden Markov Model (HMM) constructed by using consecutive actions of AI bots and improved with the initial training phase and our sliding window approach. The method is evaluated for three different performance criteria: recognition of bots, grouping bots that have similar game styles and tracking changes in the strategy of a single bot through the game. The results indicate that the method is promising with 90,04% binary classification success in average.