National Repository of Grey Literature 13 records found  1 - 10next  jump to record: Search took 0.00 seconds. 
Playing a 3D Tunnel Game Using Reinforcement Learning
Adilovic, Una ; Dingle, Adam (advisor) ; Straka, Milan (referee)
Tunnel games are a type of 3D video game in which the player moves through a tunnel and tries to avoid obstacles by rotating around the axis of the tunnel. These games often involve fast-paced gameplay and require quick reflexes and spatial awareness to navigate through the tunnel successfully. The aim of this thesis is to explore the representation of a tunnel game in a discrete manner and to compare various reinforcement learning algorithms in this context. The objective is to evaluate the performance of these algorithms in a game setting and identify potential strengths and limitations. The results of this study may offer insights on the application of discrete tabular methods in the development of AI agents for other continuous games.
Artificial Intelligence for the Card Game Durak
Zarlykov, Azamat ; Dingle, Adam (advisor) ; Rittig, Tobias (referee)
Card games with imperfect information present a unique challenge for many common game-playing algorithms because of their hidden game state. The objective of this thesis is to create a framework for implementing and testing various AI agents in the popular imperfect information card game "Durak" to identify the most effective approach in this environment. This paper presents a theoretical and experimental comparison of agents using various techniques, including rules-based heuristics, minimax search, and Monte Carlo tree search. In our analysis, we found that the Monte Carlo Tree Search agent performed the best among the implemented AI agents, whereas the rule-based heuristic agent and the minimax agent were less effective. 1
NextGen SPICE - Electrical Circuit Simulation Library for .NET
Zikmund, Radek ; Ježek, Pavel (advisor) ; Dingle, Adam Thomas (referee)
The goal of this thesis was to create an extensible library for simulating elec- trical circuits for the .NET platform, which could be used in broad contexts like development of educational programs or applications that use evolutionary algo- rithms to evolve electrical circuits. Our library is inspired by the family of SPICE programs developed at University of California, Berkeley. Initial version of our library implements the transient analysis of electrical circuits and supports basic devices like voltage and current sources, resistors, capacitors, inductors, but also semiconductor diode and BJT transistor devices. Our library is designed in such a way that both new circuit devices and circuit analyses can be added in future versions. Other features of our library include importing circuits or their parts from the industry standard SPICE netlists and ability to modify circuit parameters during the simulation. In this thesis, we also investigate using double-double precision type to improve convergence during the simulation. We also implement a simple SPICE-like console application to allow our sim- ulation library to be used from command line.
Procedurální generování vesnic ve hře Minecraft pomocí algoritmu Wave Function Collapse
Mifek, Jakub ; Černý, Vojtěch (advisor) ; Dingle, Adam (referee)
1 Maxim Gumin's Wave Function Collapse (WFC) algorithm is an example-driven image generation algorithm emerging from the craft of procedural content generation. The intended use of the algorithm is to generate new images in the style of given examples by ensuring local similarity. Our work aims to generalize the original work to make the algorithm applicable in other domains. Furthermore, we aim to apply it in a more difficult task of village generation in the 3D sandbox video game Minecraft. We will create a generic WFC library and a Minecraft mod, which will allow for structure generation using WFC. We hope that our WFC library will be beneficial to anyone exploring WFC and its applications in the Kotlin language and that our Minecraft showcase reveals some of the benefits and limits of the algorithm in complex problems.
Faker - pseudorandom object content C# generator
Průšová, Kateřina ; Ježek, Pavel (advisor) ; Dingle, Adam (referee)
The goal of this thesis was to implement Faker software library capable of filling instances of user defined classes with pseudorandom content and targeting the .NET platform. Requirements the Faker library should fulfill were based on the analysis of existing implementations of similar software libraries for various programming languages. Xoshiro256** PRNG algorithm was chosen to be used as the source of 64-bit long pseudorandom words. Faker uses pseudorandom words produced by xoshiro256** to gene- rate pseudorandom values of all basic data types available in C# programming language. Furthermore, a Source Generator is used to ensure, that the Faker can be easily exten- ded by additional categories of pseudorandom values such as first names, last names or addresses. The Faker allows to set sets of rules describing a required structure of pseudorandom data and it is subsequently capable of generating large amounts of the pseudorandom content with the specified structure. The emphasis was put on making the rule setting API as intuitive as possible and ensuring that the majority of syntactic mistakes made while stating rules is detected at compile time. 1
Aplikace hierarchických grafových gramatik v procedurálním generování světů
Svoboda, Jakub ; Černý, Vojtěch (advisor) ; Dingle, Adam (referee)
Title: Application of hierarchical graph grammars in procedural 3D world gen- eration Author: Jakub Svoboda Abstract: Procedural content generation (PCG) is an often-used technique in video games. It allows us to generate large quantities and permutations of con- tent. A common problem in utilizing PCG in level design is that it is challenging to generate content close to what a human would create in overall quality and structure. One way of solving these problems is using graph grammars to rep- resent relations in the game world. Implementing a working graph generator using graph grammars and applying it to generate worlds is not very well docu- mented. This thesis will try to overcome this problem by implementing such a generator and extending it to use hierarchical graph grammars. The generator will be used to generate a 3D open world. The generator should be suitable for levels in other types of games. Keywords: procedural content generation, game development, hierarchical graphs, graph grammars, procedural level design
Efficient forward model for Super Mario AI framework
Šosvald, David ; Gemrot, Jakub (advisor) ; Dingle, Adam (referee)
The artificial intelligence framework for Super Mario Bros. has been used in a lot of research in the past decade. We have noticed that the forward model (simulation of the game world) present in the framework is quite inefficient and thus negatively influences all work that is based on it, especially intelligent agents that utilize it. This means that every work using such agents is influenced too. That might also include level generation, where agents are often used to test the playability and properties of levels. We have implemented a more efficient forward model and as a proof of concept, we used the improved forward model to create new intelligent agents. In a benchmark we ran, the negative influence of the original forward model was confirmed, as all agents using the new forward model greatly outperformed agents based on the original one.
Performance of a Safe Compiled Language with Automatic Memory Management
Ekserdzhian, Georgii ; Dingle, Adam (advisor) ; Ježek, Pavel (referee)
In this thesis, I discuss my implementation of a memory-safe language called G and its performance. I compare it to other popular object-oriented languages like C# and C++. I try to prove that memory safety features have only a small effect on the performance of most programs. 1
Artificial intelligence for the game of Azul
Počatko, Michal ; Dingle, Adam (advisor) ; Hric, Jan (referee)
A comparison between three different approaches to developing an AI agent for the board game Azul and their implementation, testing and consequent results of said tests. A part of the thesis is also a simulator created in a game engine for playing against a local player or an artificial intelligence agent.
QUIC protocol implementation for .NET
Zikmund, Radek ; Ježek, Pavel (advisor) ; Dingle, Adam Thomas (referee)
QUIC is a general-purpose transport layer network protocol proposed as the replace- ment for TCP and TLS in HTTP/3. QUIC is based on UDP and provides always- encrypted connections able to transmit multiple streams of data in parallel. Compared to TCP, QUIC promises lower latency, better congestion control flexibility, and a solution to head-of-line blocking occurring in multiplexed HTTP/2 connections. The latest release of .NET - .NET 5 - has shipped with experimental support for QUIC based on the MsQuic C library. However, when implementing new features in stan- dard .NET libraries, purely .NET implementations are preferable to adding dependencies on native libraries because .NET implementations offer better maintainability and - in some cases - even better performance. This thesis explores the viability of a purely C# QUIC implementation as a future replacement for .NET 6 or later release. This thesis's result is a fork of the official .NET runtime repository with partial C# implementation of the QUIC protocol. We implemented a subset of the QUIC speci- fication, which is sufficient for a basic performance evaluation. As part of the thesis, we have benchmarked the throughput and latency of our and the MsQuic-based QUIC implementation and compared them to TCP's performance in two environments: LAN and...

National Repository of Grey Literature : 13 records found   1 - 10next  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.