|
|
Strategic Game Based on Multiagent Systems
Knapek, Petr ; Kočí, Radek (referee) ; Zbořil, František (advisor)
This thesis is focused on designing and implementing system, that adds learning and planning capabilities to agents designed for playing real-time strategy games like StarCraft. It will explain problems of controlling game entities and bots by computer and introduce some often used solutions. Based on analysis, a new system has been designed and implemented. It uses multi-agent systems to control the game, utilizes machine learning methods and is capable of overcoming oponents and adapting to new challenges.
|
|
|
Artificial Intelligence in Strategic Computer Games
Votroubek, Lukáš ; Přibyl, Bronislav (referee) ; Zuzaňák, Jiří (advisor)
This work covers with artificial intelligence of strategy computer games, however many of these methods are usable in other areas. These are different methods used in deciding (finite state machina, fuzzy logic, Markov Process), planning (Goal-oriented action planning, Montecarlo planning, Case-based planning) and machine learning ( Reinforcement leasing, Decision Learning and Neural Networks). Objective of this thesis is to study this methods from different sources and explain their base principle. Then few of this methods resolve in more details and implement them (goal oriented planning and state machine). This thesis focuses on game engine ORTS, which is used in implementing and testing methods.
|
|
| |
|
|
Strategic Game with Uncertainity
Gerža, Martin ; Zbořil, František (referee) ; Zbořil, František (advisor)
This thesis focuses on the implementation of a system for playing the board game Scotland Yard autonomously and also focuses on a comparison of this system with similar ones. I focused on obtaining enough information about the possible methods that should be suitable for such a system and decided to implement this system using the Monte Carlo Tree Search method. The result implementation of the system was tested against similar systems, achieving an excellent result against another system that used an equivalent method. There was achieved a balanced result against a system that used the Alpha-Beta method. The main result of this work is a working version of an autonomous system for playing the game Scotland Yard on a reduced field. It also provides the possibility of using two similar systems within a single program in order to compare their implementations.
|
|
|
Multiagent Support for Strategic Games
Knapek, Petr ; Uhlíř, Václav (referee) ; Zbořil, František (advisor)
This thesis is dedicated to creating a new system with capabilities to create new generic, autonomous strategy computer game controlling elements based on multi-agent systems with social, intelligent decision-making and learning skills. Basic types of strategy games and problems of their playing will be introduced, along with currently used methods of intelligent game AI development. This thesis also presents design and implementation of the new system, working model for a specific game and results obtained while testing it.
|
|
|
Strategy for Game Systems
Švestka, Marek ; Tóth, Michal (referee) ; Zemčík, Pavel (advisor)
This thesis resolves the artificial intelligence representation in computer games. The goal was to find it's suitable interpretation methods. The issue was solved with "map"implementation, which is the n-dimension matrix holding the information about current game state for the concrete player. There were various types of these matrixes used in this thesis. Furthermore was designed a way to evolve computer opponents during the gameplay and created an algorithm, that gives the idea of the space in which it is located. Benefit from this thesis is a solution that makes artificial adversary close to human gameplay behavior. The outcome could also be used in simulators for military battles in real world.
|
|
|
Strategic Game with Uncertainity
Sova, Michal ; Zbořil, František (referee) ; Zbořil, František (advisor)
The thesis focuses on creating an autonomous system for the game Scotland Yard by using machine learning method. The problem is solved by algorithm Monte Carlo tree search. Algorithm Monte Carlo tree search was tested against algorithm Alpha-beta. These results showed that Monte Carlo tree search algorithm is operational but win rate of this algorithm is lower than win rate of algorithm Alpha-beta. The resulting system is functional, autonomous and capable of playing the game Scotland Yard on simplified game area. There was an attempt to expand simplified version of the game Scotland Yard. In expanded version algorithm Alpha-beta was not successful because of insufficient computational resources. Algorithm Monte Carlo tree search, on the other hand, was more successful in expanded version.
|
|
|
Strategic Game with Uncertainity
Tulušák, Adrián ; Šimek, Václav (referee) ; Zbořil, František (advisor)
The thesis focuses on creating an autonomous functional system for the game Scotland Yard by using artificial intelligence methods for game theory and machine learning. The problem is solved by algorithm of game theory - Alpha Beta. There was an attempt to use machine learning, but it proved to be unsuccessful due to the large number of states for expansion and insufficient computational recourses. The solution using Alpha Beta algorithm was tested on human players and it proved the ability of artificial intelligence to fully compete against real players. The resulting system is functional, autonomous and capable of playing the game Scotland Yard on simplified game area. Based on these experiments, the thesis also introduces some improvements that could utilize machine learning and extend the existing solution.
|
|
|
Deep Learning Methods for Machine Playing the Scotland Yard Board Game
Hrkľová, Zuzana ; Janoušek, Vladimír (referee) ; Zbořil, František (advisor)
Táto práca sa zaoberá metódami hlbokého učenia, ktoré sú aplikovateľné na stolné hry s neurčitosťou. V rámci práce boli naštudované princípy učenia s posilňovaním, s hlavným zameraním na Q-learning algoritmy, spomedzi ktorých bol vybraný Deep Q-Network algoritmus. Ten bol následne implementovaný na zjednodušených pravidlách stolnej hry Scotland Yard. Konečná implementácia bola porovnaná s metódami Alpha-Beta a Monte Carlo Tree Search. S výsledkov vyplinulo, že schovávaný hráč riadený DQN algoritmom predstavoval pre ostatné metódy najťažšieho protihráča, narozdiel od hľadajúcich hráčov, ktorým sa nepodarilo zlepšiť existujúce riešenia. Napriek tomu, že implementovaná metóda nedosiahla lepšie výsledky oproti doposiaľ existujúcim metódam, ukázalo sa, že potrebuje najmenej výpočetných zdrojov a času na vykonanie daného ťahu. To ju robí najperspektívnejšou zo spomínaných metód na budúcu možnú implementáciu originálnej verzie danej hry.
|
|
| |
guest ::
