National Repository of Grey Literature 69 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Using evolution algorithms for creating AI controllers for tank models
Šijanov, Denis ; Gemrot, Jakub (advisor) ; Pilát, Martin (referee)
Title: Using genetic algorithms to create AI tank model controllers Author: Denis Šijanov Department: Department of Software and Computer Science Education Supervisor: Mgr. Jakub Gemrot, Ph.D., Department of Software and Computer Science Education Abstract: Genetic algorithm is a general procedure designed for solving equations that do not have an algorithm or a better way of solving them yet. In addition this process can be explained even by using simple examples, which makes it an interesting exercise for students of computer science. The students may encounter varying forms of publication of these algorithms such as videos or controlled simulations. These forms of presentation may help the subjects understand the basic principles of an algorithm, but they are not interactive. The students therefore can't apply their ideas and find out what impact on the algorithm they would have had. Details such as these are very important when trying to understand genetic algorithms. There are applications which solve user defined problems by using genetic algorithms. They demonstrate the usability of the algorithm, but they do not help the users understand the algorithm. The most efficient way to understand genetic algorithms in my opinion is to write one on your own. This is why I have decided to create an...
Grid-based Online Multiplayer Strategy Game
Fibich, Michal ; Gemrot, Jakub (advisor) ; Bída, Michal (referee)
Title: Grid-based Online Multiplayer Strategy Game Author: Michal Fibich Department: Department of Software and Computer Science Education Supervisor: Mgr. Jakub Gemrot, Ph.D., Department of Software and Computer Science Education Abstract: Playing a massively multi-player on-line real-time strategy game is connected with expectation of playing with other players close to your position in the game. Some games of this kind have a very long life cycle where the progress of each player is persistent. A match can take months, even years to finish. However, every match is very dependent on the amount of participants which is not always ideal. Different seasons of the year can cause massive drops in the amount of players. There have already been attempts to incorporate an artificial intelligence to these matches, but the goal was to provide a win condi- tion instead of fighting a decreasing player base. That is why we have started developing a framework which includes the basic mechanics of the game and al- lows customization of basic game elements such as units, resources, buildings or entire nations. Part of the framework is an artificial intelligence which is capable of playing games created using the framework along with players. The problem was to find a proper behaviour for the artificial intelligence that...
Security Game with Planning Agents
Ohman, Ľubomír ; Gemrot, Jakub (advisor) ; Hric, Jan (referee)
The goal of the thesis was to create an application for training security guards, containing a configurable artificial burglar. To fulfill these expectation, a 3D application was implemented, containing a 2D editor of security objects. In order to be able to implement the burglar, we analyzed his objectives and designed an algorithm capable of planning his actions and dealing with the multi- objective optimization. Finally, we compared the performance of our proposed solution to the state- of-the-art algorithm to prove that it solved the optimization more efficiently in our case.
Procedural Generation of Endless Runner Type of Video Games
Černý, Vojtěch ; Gemrot, Jakub (advisor) ; Pilát, Martin (referee)
Procedural content generation (PCG) is increasingly used to generate many aspects in a variety of games. AI players, both hand scripted or also generated (by AI methods), are used to evaluate this content. Comparatively little effort is invested in using PCG to generate the whole game, including its rules. In this thesis, we use evolutionary algorithms to generate the game rules, its content and the evaluating AI player on a narrow, but flourishing, genre of endless runners - games where the player is constantly running. For this purpose, we have implemented a framework for creating endless runner games. Our approach could provide more efficiency for game designers, explore completely new game concepts in endless runners, platformer games, and be further generalized to other game genres.
Artificial Intelligence for Children of the Galaxy Computer Game
Šmejkal, Pavel ; Gemrot, Jakub (advisor) ; Trunda, Otakar (referee)
Even though artificial intelligence (AI) agents are now able to solve many classical games, in the field of computer strategy games, the AI opponents still leave much to be desired. In this work we tackle a problem of combat in strategy video games by adapting existing search approaches: Portfolio greedy search (PGS) and Monte-Carlo tree search (MCTS). We also introduce an improved version of MCTS called MCTS considering hit points (MCTS_HP). These methods are evaluated in context of a recently released 4X strategy game Children of the Galaxy. We implement a combat simulator for the game and a benchmarking framework where various AI approaches can be compared. We show that for small to medium combat MCTS methods are superior to PGS. In all scenarios MCTS_HP is equal or better than regular MCTS due to its better search guidance. In smaller scenarios MCTS_HP with only 100 millisecond time limit outperforms regular MCTS with 2 second time limit. By combining fast greedy search for large combats and more precise MCTS_HP for smaller scenarios a universal AI player can be created.
Master of the Carpet: A 3D first-person action game
Kuchyňová, Karolína ; Ježek, Pavel (advisor) ; Gemrot, Jakub (referee)
The goal of this thesis is to reimplement the old DOS game Magic Carpet using modern game development means provided by the Unity engine. In the game, the player controls a wizard on a ying carpet, whose task is to collect speci ed amount of mana. He travels through a 3D game world, casts spells, builds castles, where his mana is stored, and ghts various types of monsters or enemy wizards. A detailed analysis of the original game can be found in the introductory part of the thesis. Within problem analysis, we discuss the possible approaches to creating a nite but borderless game world and ways of implemen- ting arti cial intelligence and its movemenent system for monsters and enemy wizards. The game world terrain is generated procedurally therefore a special chapter is devoted to this topic. The work also contains an extension of the ori- ginal Unity Editor called Level Designer, where new game levels can be created.
Artificial player for Dota 2
Kočur, Jan ; Gemrot, Jakub (advisor) ; Parízek, Pavel (referee)
Dota 2 is one of the most popular strategic computer games of the Multiplayer Online Battle Arena (MOBA) genre. MOBA games are based on teamwork and tactical thinking. That makes them an interesting platform for the artificial intelligence (AI) research, that aims to create artificial agents capable of playing the game. However, there does not exist any framework, that would allow the development of complex agents. First, we developed a framework that allows the creation of agents for Dota 2 in Java. Second, we implemented an agent above the framework, that is capable of playing the game.We have divided the work into two parts. First, we have analyzed requirements for our framework and described its architecture. Second, we have analyzed Dota 2 from the AI perspective and implemented agents above our framework. Our agents were capable of playing the game. The framework can be used for further research.
Umělý hráč pro Angry Birds
Nikonova, Ekaterina ; Gemrot, Jakub (advisor) ; Matzner, Filip (referee)
Angry Birds is a popular video game, in which the player is provided with a sequence of birds to shoot from a slingshot. The task of the game is to kill all green pigs with maximum possible score. Angry Birds appears to be a difficult task to solve for artificially intelligent agents due to the sequential decision-making, nondeterministic game environment, enormous state and action spaces and requirement to differentiate between multiple birds, their abilities and optimum tapping times. In this thesis, we are presenting several different techniques suitable for the implementation of artificial Angry Birds agent. First, we will show how limited Breath First Search can be used to estimate potentially good shooting points. After that we will discover how reinforcement learning can be applied to the Angry Birds game. Lastly, we will apply Deep reinforcement learning to Angry Birds game by implementing Double Dueling Deep Q- networks. One of our main goals was to build an agent that is able to compete in AIBirds competition and with humans on the game's first 21 levels. In order to do so, we have collected a dataset of game frames that we used to train our agent. We evaluate our agents using results of the previous participants of AIBirds competition and results of volunteer human players.
Evolutionary Algorithm-based Procedural Level Generator for a Rogue-like Game
Vegricht, Jan ; Gemrot, Jakub (advisor) ; Zelinka, Mikuláš (referee)
Title: Evolutionary Algorithm-Based Procedural Level Generator for a Rogue-like Game Author: Jan Vegricht Department: Department of Software and Computer Science Education Supervisor: Mgr. Jakub Gemrot, Ph.D., Department of Software and Computer Science Education Abstract: Rogue-like games are genre with long tradition in game industry. One significant factor commonly associated with this genre is procedural level generation. The goal of this thesis is to design and implement a level generator for one concrete rogue-like game using evolutionary algorithms as main means of generation. Methods and results are then compared to non-evolutionary alternative algorithms, attempting to generate comparable solutions. The results seem to indicate that while evolutionary algorithms can be used to generate dungeons, practicality of this approach is for the most part limited. Keywords: evolutionary algorithms, procedural generation, constrained optimization, rogue-like
Artificial Intelligence for Spelunky Computer Game
Závorka, Kamil ; Gemrot, Jakub (advisor) ; Ježek, Pavel (referee)
Spelunky is one of the desktop games, where player control agent in labyrinth and his task is to reach the exit. In this labyrinth there are many threats and quests, which makes the game interesting for making artificial intelligence, that can be adjusted for these threats and quests. The goal of this work was to create a framework for comfortable programming of artificial intelligence for this game. Although there is a tool named SpelunkBotAPI for its writing and executing, the API of this tool provides only basic controlling of agent and it is hard to use it. The approach, that I chose for this work, used the existing API and built a framework above it, that will be easier to use. For more intuitive using of the framework, this work crates GOAP (Goal Oriented Action Planner), that uses its functionality for reaching goals specified by the programmer.

National Repository of Grey Literature : 69 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.