Thesis Details
Umělá inteligence pro hraní her
The focus of this work is the use of artificial intelligence methods for a playing of real-time strategic (RTS) games, where all interactions of players are performed in real time (in parallel). The thesis deals mainly with the use of machine learning method Q-learning, which is based on reinforcement learning and Markov decision process. The practice part of this work is implemented for StarCraft: Brood War game.A proposed solution learns to make up an optimal order of buildings construction in respect to a playing style (strategy) of the opponent(s). The solution is proposed within the rules of the SSCAIT tournament. Analysis and evaluation of the proposed system are based on a comparison with other participants of the competition as well as a comparison of the system behavior before and after the playing of a set of the games.
artificial intelligence, StarCraft: Brood War, Q-learning, reinforcement learning, Real-Time Strategy games, SSCAIT
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Hliněná Dana, doc. RNDr., Ph.D. (DMAT FEEC BUT), člen
Matoušek Petr, doc. Ing., Ph.D., M.A. (DIFS FIT BUT), člen
Zachariášová Marcela, Ing., Ph.D. (DCSY FIT BUT), člen
@bachelorsthesis{FITBT19998, author = "V\'{a}clav Bayer", type = "Bachelor's thesis", title = "Um\v{e}l\'{a} inteligence pro hran\'{i} her", school = "Brno University of Technology, Faculty of Information Technology", year = 2017, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/19998/" }