|
|
Controller design with using CARLA method
Jasanský, Michal ; Houška, Pavel (referee) ; Březina, Tomáš (advisor)
This bachelor thesis is focused on the application repeatedly reinforcement learning method named „Continuous Action Reinforcement Learning Automata“ (CARLA). There is recapitulated a basic describe of the artificial intelligence method, however it deals mainly with the CARLA method. In the thesis are described the advantages, disadvantages and the type of mathematical basis for simplified version of the CARLA method. The main part of the thesis is concerned with the method testing and debugging. The influence of the setting the parameters is also demonstrated in the thesis. The method is successfully applied on two systems: DC motor and physical pendulum.
|
|
|
Intelligent Music Player for Android
Tomášek, Michal ; Rozman, Jaroslav (referee) ; Kalmár, Róbert (advisor)
Today's market is full of different kinds of music players. However there is no music player using prediction, which would be able to work with usual usage and in real time. This bachelor's thesis deals with the design and implementation of a music player with implemented prediction. The creation of high quality architecture for this application and the choice of appropriate prediction algorithm are emphasized. At first, the category of methods of machine learning and afterwards the algorithm are determined. The final prediction algorithm is divided into a several sections, therefore it is necessary to pick or create a solution for all its parts. The outcome of this project is the music player for Android OS which would be able to predict and learn from a user interaction in real time.
|
|
|
Research on Reliable Low-Power Wide-Area Communications Utilizing Multi-RAT LPWAN Technologies for IoT Applications
Štůsek, Martin ; Grochla, Krzysztof (referee) ; Curado, Marilia (referee) ; Hošek, Jiří (advisor)
Předkládaná disertační práce je zaměřena na „Výzkum spolehlivé komunikace pro IoT aplikace v bezdrátových sítích využívajících technologie Multi-RAT LPWAN“. Navzdory značnému pokroku v oblasti vývoje LPWA technologií umožňující masivní komunikace mezi zařízeními (mMTC), nemusí tyto technologie výkonnostně dostačovat pro nově vznikající aplikace internetu věcí. Hlavním cílem této disertační práce je proto nalezení a vyhodnocení limitů současných LPWA technologií. Na základě těchto dat jsou nevrženy nové mechanismy umožňující snazší plánování a vyhodnocování síťového pokrytí. Navržené nástroje jsou vyladěny a validovány s využitím dat získaných z rozsáhlých měřících kampaních provedených v zákaznických LPWA sítích. Tato disertační práce dále obsahuje návrh LPWA zařízení vybavených více komunikačními rozhraními (multi-RAT) které mohou umožnit překonání výkonnostních limitů jednotlivých LPWA technologií. Současná implementace se zaměřuje zejména na snížení spotřeby zařízení s více rádiovými rozhraními, což je jejich největší nevýhodou. K tomuto účelu je využito algoritmů strojového učení, které jsou schopné dynamicky vybírat nejvhodnější rozhraní k přenosu.
|
|
|
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.
|
|
|
Reinforcement Learning for Robotic Soccer Playing
Brychta, Adam ; Švec, Tomáš (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to create a reinforcement learning agent that is able to play a soccer. I'm working with the deep Q-learning algorithm, which uses deep neural network. The practical part of this work is about implementing the agent for reinforcement learning. The goal of the agent is to choose the best action possible for a given situation. The agent is being trained in a variety of scenarios. The result of this thesis shows an approach to control soccer player using machine learning.
|
|
|
Reinforcement Learning for 3D Games
Beránek, Michal ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
Thesis deals with neural network learning on simple tasks in 3D shooter Doom, mediated by research platform ViZDoom. The main goal is to create an agent, which is able to learn multiple tasks simultaneously. Reinforcement learning algorithm used to achieve this goal is called Rainbow, which combines several improvements of DQN algorithm. I proposed and experimented with two different architectures of neural network for learning multiple tasks. One of them was successful and after a relatively short period of learning it reached almost 50% of maximum possible reward. The key element of this achievement is an Embedding layer for parametric description of task environment. The main discovery is, that Rainbow is able to learn in 3D environment and with the help of Embedding layer, it is able to learn on multiple tasks simultaneously.
|
|
|
Navigation Using Deep Convolutional Networks
Skácel, Dalibor ; Veľas, Martin (referee) ; Hradiš, Michal (advisor)
In this thesis I deal with the problem of navigation and autonomous driving using convolutional neural networks. I focus on the main approaches utilizing sensory inputs described in literature and the theory of neural networks, imitation and reinforcement learning. I also discuss the tools and methods applicable to driving systems. I created two deep learning models for autonomous driving in simulated environment. These models use the Dataset Aggregation and Deep Deterministic Policy Gradient algorithms. I tested the created models in the TORCS car racing simulator and compared the result with available sources.
|
|
|
Deep reinforcement learning and snake-like robot locomotion design
Kočí, Jakub ; Dobrovský, Ladislav (referee) ; Matoušek, Radomil (advisor)
This master thesis is discussing application of reinforcement learning in deep learning tasks. In theoretical part, basics about artificial neural networks and reinforcement learning. The thesis describes theoretical model of reinforcement learning process - Markov processes. Some interesting techniques are shown on conventional reinforcement learning algorithms. Some of widely used deep reinforcement learning algorithms are described here as well. Practical part consist of implementing model of robot and it's environment and of the deep reinforcement learning system itself.
|
|
|
Robot path planning by means of reinforcement learning
Veselovský, Michal ; Liška, Radovan (referee) ; Dvořák, Jiří (advisor)
This thesis is dealing with path planning for autonomous robot in enviromenment with static obstacles. Thesis includes analysis of different approaches for path planning, description of methods utilizing reinforcement learning and experiments with them. Main outputs of thesis are working algorithms for path planning based on Q-learning, verifying their functionality and mutual comparison.
|
|
|
Machine Learning in Strategic Games
Vlček, Michael ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
Machine learning is spearheading progress for the field of artificial intelligence in terms of providing competition in strategy games to a human opponent, be it in a game of chess, Go or poker. A field of machine learning, which shows the most promising results in playing strategy games, is reinforcement learning. The next milestone for the current research lies in a computer game Starcraft II, which outgrows the previous ones in terms of complexity, and represents a potential new breakthrough in this field. The paper focuses on analysis of the problem, and suggests a solution incorporating a reinforcement learning algorithm A2C and hyperparameter optimization implementation PBT, which could mean a step forward for the current progress.
|
guest ::
