|
|
Simulation of Entities Collective Behavior in Virtual World
Vymazal, Tomáš ; Žák, Pavel (referee) ; Láník, Aleš (advisor)
Theme of this work is to evaluate and compare aviable paradigms for entity control in virtual worlds, and to implement one of these paradigms in application. Dynamic finite state machine upgraded using genetic algorithms has been chosen. This paradigm should make agent's behavior better and adapt agent to required state: i.e. make agent harvest resources in virtual world. Output of this work is application for running evolution and application for 3D view of agent's behavior.
|
|
|
Deep Learning AI in Game Environments
Glós, Kristián ; Bobák, Petr (referee) ; Polášek, Tomáš (advisor)
This thesis is focused on analysing deep learning algorithms and their ability to complete given tasks implemented in game environments created via the Unity game engine. Secondary objective was to research and specify possible use-cases of deep learning during game development. The algorithms used fall into Reinforcement learning, Imitation learning and Neuroevolution, while Reinforcement learning was used throughout the whole game scene development cycle. Analysis and results were collected through training the networks in different game scene states and other factors.
|
|
|
Training Intelligent Agents in Unity Game Engine
Vaculík, Jan ; Chlubna, Tomáš (referee) ; Matýšek, Michal (advisor)
The goal of this work is to design applications, which demonstrate the power of machine learning in video games. To achieve this goal, this work uses the ML-Agents toolkit, which allows the creation of intelligent agents in the Unity Game Engine. Furthermore, a series of experiments showing the properties and flexibility of intelligent agents in several real-time scenarios is presented. To train the agents, the toolkit uses reinforcement learning and imitation learning algorithms.
|
|
|
Simulation of Negotiation and Argumentation Protocols
Říha, Michal ; Samek, Jan (referee) ; Zbořil, František (advisor)
This work deals with communication in multiagent systems. The protocols for negotiation and argumentation are shown, and model example of their usage is described. We describe hierarchical model of trust in contexts, that is used for representation of agent's believes. The argumentation protocol for those agents is designed, and is used for solving conflicts.
|
|
|
Indoor Air Quality Assessment
Doležal, Libor ; Fišer, Jan (referee) ; Krejčí, Vladimír (advisor)
The thesis inform the reader about the agents that affect the indoor air quality, especially those related to thermal comfort. It also draws attention to discomfort caused by some of the agents. There are introduced basic methods and measurement procedures of quantities necessary to evaluate the thermal comfort. The thesis is not a direct manual to the measurement of the mentioned quantities but it guides the reader to the most suitable measuring instrument according to the measurement objective and range. Further it provides a review of standards and public notices related to this theme.
|
|
|
Multirobot Path Planning in a Dynamic System
Dokoupil, Ladislav ; Veigend, Petr (referee) ; Zbořil, František (advisor)
This thesis deals with the problem of dynamic environment search using multi-agent systems. The primary result of this work is participation in the MAPC2022 contest, but the application can be found in the exploration of unknown space, assuming finite visibility and unlimited distance of communication of the agents. After describing the current methods for solving the given problem and their limitations, an algorithm based on ant colony optimization is proposed. Graphs were then created with data from running program with various parameters. The result of work is agents synchronization improvements and overall optimization of the platform involved in the mentioned contest from previous year. As a result half more of explored space was measured compared to previous solution.
|
|
|
Prevention of nosocomial infections origin and spreading in Český Krumlov a.s. hospital
KOCOURKOVÁ, Lenka
The present Bachelor thesis focuses primarily on the prevention of occurrence of hospital-acquired infections and the causes of spread of these infections across healthcare facilities. The thesis relies on active communication with the coordinator for management of quality and safety of nursing care, who helpfully provided me with valid information and documents relating to the system of hospital-acquired infection prevention, and arranged for sampling for microbiological examinations in postoperative care departments (ONP) - ONP II and ONP - C III, the hospital Nemocnice Český Krumlov a.s. The Bachelor thesis consists of a theoretical part and a practical part. The theoretical part summarizes knowledge related to nosocomial infections as such, the division and manner of transmission, with an emphasis of prevention of occurrence of these infections and spread of the same among "healthy hospitalized persons." The practical part explores the hospital's approved internal documents aimed at prevention of nosocomial infections and training of staff in the healthcare facility. Moreover, the practical part also verifies the prevention of nosocomial infections by means of microbiological tests. The entire research was carried out in cooperation with two hospitals: Nemocnice Český Krumlov a.s., i.e. the location of sampling, and Nemocnice a.s. Prachatice, the location of microbiological processing. The laboratory-based research part was solved in a microbiology laboratory in the hospital Nemocnice Prachatice a.s., with the aim of identifying the individual microorganisms from the smears taken in the postoperative care department in the hospital in Český Krumlov. These smears reflect the quality of the performed hygiene in connection with the risk of occurrence of nosocomial infections. In addition to laboratory-based research activities, the present thesis also examines the current quality and processing of the hospital's internal documents relating to the prevention of nosocomial infections and the training schedule for the hospital's staff in this respect - trainings are conducted on an annual basis. The thesis is concluded by a summary of isolated microorganisms and comparison of these microorganisms in the framework of the two hospital departments. Last but not least, the presence of highly infectious agents for occurrence of nosocomial infections is excluded on the basis of valid legislation. The thesis also provides a result of qualitative processing in a form of recommendations e.g. for improvement of purpose-directed cleaning. The thesis may therefore be used as a tool for improving awareness of this problem area.
|
|
|
Multirobot Path Planning in a Dynamic System
Dokoupil, Ladislav ; Veigend, Petr (referee) ; Zbořil, František (advisor)
This thesis deals with the problem of dynamic environment search using multi-agent systems. The primary result of this work is participation in the MAPC2022 contest, but the application can be found in the exploration of unknown space, assuming finite visibility and unlimited distance of communication of the agents. After describing the current methods for solving the given problem and their limitations, an algorithm based on ant colony optimization is proposed. Graphs were then created with data from running program with various parameters. The result of work is agents synchronization improvements and overall optimization of the platform involved in the mentioned contest from previous year. As a result half more of explored space was measured compared to previous solution.
|
|
|
Training Intelligent Agents in Unity Game Engine
Vaculík, Jan ; Chlubna, Tomáš (referee) ; Matýšek, Michal (advisor)
The goal of this work is to design applications, which demonstrate the power of machine learning in video games. To achieve this goal, this work uses the ML-Agents toolkit, which allows the creation of intelligent agents in the Unity Game Engine. Furthermore, a series of experiments showing the properties and flexibility of intelligent agents in several real-time scenarios is presented. To train the agents, the toolkit uses reinforcement learning and imitation learning algorithms.
|
|
|
Deep Learning AI in Game Environments
Glós, Kristián ; Bobák, Petr (referee) ; Polášek, Tomáš (advisor)
This thesis is focused on analysing deep learning algorithms and their ability to complete given tasks implemented in game environments created via the Unity game engine. Secondary objective was to research and specify possible use-cases of deep learning during game development. The algorithms used fall into Reinforcement learning, Imitation learning and Neuroevolution, while Reinforcement learning was used throughout the whole game scene development cycle. Analysis and results were collected through training the networks in different game scene states and other factors.
|
guest ::
