National Repository of Grey Literature 170 records found  beginprevious76 - 85nextend  jump to record: Search took 0.00 seconds. 
Neuroevolution-based AI for the Dominion game
Machala, Patrik ; Kuboň, David (advisor) ; Holan, Tomáš (referee)
The subject of this thesis is a simple user interface for the base version of the card game Dominon and the development of an artificial intelligence capable of playing this game. The AI is designed regardless of the initial configuration of the game. That allows an immediate start without waiting for the evolution of the opponent. The basis of this scheme is a recurrent neural network evolved by neuroevolution of its weights. Its inputs are made from representation of current game state and its output is the valuation of cards, which leads to their purchase. Second part of a player's move, the so-called action phase, is controlled by heuristics. The thesis is not limited to a single method of AI development but compares different types of evolution and different numbers of neurons in the hidden layer. According to the completed experiments the neural network evolved by competitive co-evolution with populations swapped according to their skill was the strongest opponent. Results of AI development are then compared with conclusions made on the basis of other artificial intelligencies for the Dominion game with most of these confirmed.
Didactic graph visualisation
Frantál, Jiří ; Pergel, Martin (advisor) ; Holan, Tomáš (referee)
This thesis deals with the design of programming language specialized in visu- alisation of graph algorithms, creating its interpreter and integrated development environment. The aim was to make the created program usable for education of graph algorithms and their implementation, especially at high school. Based on didactic knowledge, we designed language similar to Pascal, but adapted for the needs of graph algorithms. Part of the thesis is also brief introduction to inter- preters and several exemplary graphs and algorithms ilustrating work with our program. 1
Thebes
Heřman, Adam ; Holan, Tomáš (advisor) ; Ježek, Pavel (referee)
The goal of this bachelor thesis was to implement the board game Thebes, including graphical user interface and artificial intelligence. The game is for two to four players, who take turns on a single computer. An arbitrary amount of players can be replaced by AI agents.
Artificial intelligence for Sushi Go!
Filek, Jiří ; Holan, Tomáš (advisor) ; Mráz, František (referee)
The thesis deals with an artificial intelligence for a Sushi Go! card game. It is a game with simultaneous moves for two to five players. The thesis presents multiple approaches for development of an artificial intelligence. The main focus is on methods based on the MCTS algorithm, namely DUCT and EXP3. An artificial intelligence using weighted rules is tried as well. The weights are assigned by a genetic algorithm. The first part of the thesis is about game analysis and description of chosen methods. The second part of the thesis is about parameter tuning and comparison of different agents for two or more players. The comparison is based on a large number of games played between agents. The last part of the thesis deals with an implementation. A graphical and a console applications were created for the purpose of developing an artificial intelligence. The console application is used for parameter tuning and also to compare artificial intelligences. The graphical application is used for a game of human against artificial intelligence or other humans on a single computer. Overall, DUCT performs best in every experiment despite its theoretical disadvantages.
Theater lighting system control
Hrbáček, Matěj ; Ježek, Pavel (advisor) ; Holan, Tomáš (referee)
In the "Ochotnický soubor Lípa" theater, it is necessary to control custom-made lighting communicating via UDP datagrams. The goal of this theses is to create a system in which it will be possible to control these lights through a computer application. The ObjectsForLights library, created within the system, is portable and serves as a logical basis for user applications. The library contains client and server modules. The system is built centrally, where the server is a common point for communication with both clients and devices. The server and client modules take care of maintaining data for devices, communication with each other. The server is also responsible for direct communication with controlled lights themselves. Computer applications were created on top of the client and server modules, and enable user control of individual devices. Applications provide graphical controls for individual devices corresponding to the type of controlled device, provide ability to assign names to individual devices and create groups of controlled devices. Data for the device can then be saved and retrieved from files. 1
Evolution of artificial intelligence for turn-based strategy game
Roztočil, Ondřej ; Holan, Tomáš (advisor) ; Pergel, Martin (referee)
This thesis deals with the development of artificial intelligence for a simplified version of turn- based strategy game Advance Wars. Our focus is on comparing traditional ''ad-hoc'' game AI methods with methods that minimize the dependance on domain knowledge of the game. First part of the thesis contains analysis of the game, survey of selected game AI techniques and an overview of the implemented agents using decision trees, utility-based methods and neural networks. We present the results of our experiments with learning agent parameters and neural network weights using genetic algorithms and evolutionary strategies. We expe- rimented with training agents against fixed opponents and with competitive coevolution. In the second part we present the created software in detail. An efficient game simulator and a set of utility tools were implemented to support the AI development. A full-fledged graphical client that allows for both human and AI gameplay was also created.
Templating system for email management and generation
Kumstýř, Josef ; Ježek, Pavel (advisor) ; Holan, Tomáš (referee)
The goal of this thesis was was to create a template engine that will replace and improve existing template engine used by e-shop Alza.cz. The purpose of this system is template management and generating messages (HTML emails, SMS, etc.) from them. Part of the task was also to preserve the functionality of existing templates from the original template engine. The subject of this software solution is a template engine that uses RazorLight library and so its templates use C# language within Razor syntax. Because both original and new template engines have different syntax, part of the solution is also to create a translator from old syntax to the new one. In the text part of the thesis, we present at first the definition of a template engine. Next, we describe the original template engine including its shortcomings and limitations. We also present detail design, analysis, and development of the new template engine and syntax translator. In the end, we describe the structure of the new template engine and show how to run and use it locally. 1
Public Transport Timetables
Riedel, Lukáš ; Zavoral, Filip (advisor) ; Holan, Tomáš (referee)
It is in the interest of people using public transport to get to the desired location as quickly as possible. That is the reason they use search engines to search journeys. Most existing search engines are limited to a predetermined area or can only be used with a permanent internet connection, which may limit the user. For this reason, we have designed a customizable application system that allows the user, under certain conditions, to search without the need for an Internet connection. In the thesis we analyse mainly with the ways of finding journeys in timetables. Our solution uses an innovative algorithm that, with its operation and time required to execute a request, deviates significantly from most existing solutions. For the convenience of the user, we have developed a desktop and mobile application that provides the user user-friendly interface that can be used to search timetables and display current traffic information. 1
Computer Science Education at Grammar Schools
Lessner, Daniel ; Holan, Tomáš (advisor) ; Salanci, Ľubomír (referee) ; Černochová, Miroslava (referee)
Title: Computer Science Education at Grammar Schools Author: Daniel Lessner Department: Department of Software and Computer Science Education Supervisor: RNDr. Tomáš Holan, Ph.D., Department of Software and Computer Science Education Abstract: Computer science is not a required component of general education in Czechia. The lack of published local experience impedes the search for general agreement in basic questions, such as: Is computer science in general education possible? Is it beneficial? What educational goals should it have, what topics should it cover? The goal of this thesis is to offer empirically verified answers to these questions, considering grammar school level (students 15-18 years old) in Czechia. A set of fundamental ideas of computer science has been identified and used to develop an introductory course. The course was repeatedly tested, evaluated and improved, following the design-based research methodology. The level of students' achieve- ments as well as their own view of the novel approach to teach "informatics" was tracked. Contrary to the widely held belief (in Czechia), it turned out that computer science in general secondary education is possible and beneficial for the students, as long as the level of difficulty and specific goals are chosen appro- priately. The course is...
Artificial intelligence and game strategy in Carcassonne board game
Nekvinda, Michal ; Holan, Tomáš (advisor) ; Kuboň, David (referee)
The bachelor paper deals with the development of artificial intelligence for the Carcassonne board game for two to five players. Different approaches to creating a suitable game strategy are presented. Then, selected strategies are tested. Most of the paper is dedicated to the development by means of genetic algorithms. The paper presents detailed results of the comparison of all implemented artificial intelligences. In addition, it explains how the most successful decision-making method works. The most advanced artificial intelligences are capable of defeating human players. Additionally, the game environment for this game was implemented. It provides a graphical user interface application that offers a human-to-computer gameplay and a simple console application to perform the artificial intelligence performance tests.

National Repository of Grey Literature : 170 records found   beginprevious76 - 85nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.