|
|
Five in a Row
Vrtílek, Michal ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
This Bachelor's Thesis describes the desing and implementation of artificial intelligence for the board game Five in a row. The main goal of this thesis is to create an application able to communicate with the Manager For Board Games with the use of network communication and being able to play the board game Five in a row on a suitable level. This work contains theoretical parts about the history and rules of Five in a row and it's variations, about the possibilities of use of artificial intelligence in this game and about the structure of aplications used for playing it. It's concern is about the actual desing and implementation of said application, including it's controls. In the end I evaluate achieved results and propose additional directions for the program development.
|
|
|
Gomoku Game
Basovník, Martin ; Dluhoš, Ondřej (referee) ; Kněžík, Jan (advisor)
This bachelor's thesis is focused on the development of arti cial intelligence for board game Gomoku. Firstly it describes the necessary theoretical basis for the development of intelligent opponents. Secondly it considers the possibility of parallelization. Next it describes the implementation of the game Gomoku. Finally it documents testing process, publishes the results of the development, and outlines possible further extensions to the application.
|
|
|
Playing Gomoku with Neural Networks
Bako, Matúš ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The goal of this thesis is to create an artificial intelligence for playing Gomoku. While conventional methods usually use state space search combined with predefined rules, this artificial intelligence uses state space search and learned neural networks. A strategic network computes probability distribution for given a board state and a value network determines outcome of the game from a given board state. I trained multiple architectures of neural networks with different number of convolutional layers and different sizes of convolution kernels. Experiments show, that it is problematic to end a game without using the value network or search algorithm, but the strategic network can be used as a heuristic for choosing next move. Despite using relatively small dataset, created artificial intelligence is capable of beating weaker programs from Gomocup competition.
|
|
|
Manager for Board Games
Kouřil, Jan ; Zbořil, František (referee) ; Rozman, Jaroslav (advisor)
The main goal of this bachelor work was to remove errors from actual programming, to implement possibility of arranging different forms of tournaments and to add support for games gomoku, checkers, chess and go. It was also necessary to programm possibility of human play for better debugging of artificial intelligences, which are playing against each other in this manager. As a minor goal i would mention implementation of standard protocol in game gomoku, which supports connection for universal artificial intelligences. From begginning I discuss theoretical solutions of given problem, board games, their rules and algorithm proposal. Next, there is a summary of implementation and its realization. In the end posible extentions of manager are mentioned.
|
|
|
Support for Playing Board Games Demonstration on Mobile Platforms
Široký, Ondřej ; Kočí, Radek (referee) ; Zbořil, František (advisor)
The aim of this bachelor's thesis is to create a mobile application for the Android platform that will help the player determine the best possible move from the captured image. The application identifies the game and extracts its current state by using OpenCV library functions. This information is then displayed to the user, who has the ability to manually adjust the game status if the game board is inaccurately read. Subsequently, the application uses the Minimax algorithm with Alpha-beta pruning to determine the best move and displays it to the user.
|
|
|
Manager for Board Games
Kusák, Jiří ; Jurka, Pavel (referee) ; Rozman, Jaroslav (advisor)
The main goal of this work is to design and realize an application for managing two programs playing against each other. At the beginning I'm discussing board games (especially their rules) and player's skill rating systems. Then there is short analysis of the actual situation in this area. Fundamental part of the work is the description of the designing and realization of the manager. After that there is short description how to control the application. In the end I'm evaluating achieved results and proposing additional directions for the program development.
|
|
|
Support for Playing Board Games Demonstration on Mobile Platforms
Široký, Ondřej ; Kočí, Radek (referee) ; Zbořil, František (advisor)
The aim of this bachelor's thesis is to create a mobile application for the Android platform that will help the player determine the best possible move from the captured image. The application identifies the game and extracts its current state by using OpenCV library functions. This information is then displayed to the user, who has the ability to manually adjust the game status if the game board is inaccurately read. Subsequently, the application uses the Minimax algorithm with Alpha-beta pruning to determine the best move and displays it to the user.
|
|
|
Playing Gomoku with Neural Networks
Bako, Matúš ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The goal of this thesis is to create an artificial intelligence for playing Gomoku. While conventional methods usually use state space search combined with predefined rules, this artificial intelligence uses state space search and learned neural networks. A strategic network computes probability distribution for given a board state and a value network determines outcome of the game from a given board state. I trained multiple architectures of neural networks with different number of convolutional layers and different sizes of convolution kernels. Experiments show, that it is problematic to end a game without using the value network or search algorithm, but the strategic network can be used as a heuristic for choosing next move. Despite using relatively small dataset, created artificial intelligence is capable of beating weaker programs from Gomocup competition.
|
|
|
Manager for Board Games
Kusák, Jiří ; Jurka, Pavel (referee) ; Rozman, Jaroslav (advisor)
The main goal of this work is to design and realize an application for managing two programs playing against each other. At the beginning I'm discussing board games (especially their rules) and player's skill rating systems. Then there is short analysis of the actual situation in this area. Fundamental part of the work is the description of the designing and realization of the manager. After that there is short description how to control the application. In the end I'm evaluating achieved results and proposing additional directions for the program development.
|
|
|
Gomoku Game
Basovník, Martin ; Dluhoš, Ondřej (referee) ; Kněžík, Jan (advisor)
This bachelor's thesis is focused on the development of arti cial intelligence for board game Gomoku. Firstly it describes the necessary theoretical basis for the development of intelligent opponents. Secondly it considers the possibility of parallelization. Next it describes the implementation of the game Gomoku. Finally it documents testing process, publishes the results of the development, and outlines possible further extensions to the application.
|
guest ::
