|
|
Vehicle Control via Reinforcement Learning
Maslowski, Petr ; Uhlíř, Václav (referee) ; Šůstek, Martin (advisor)
The goal of this thesis is a creation of an autonomous agent that can control a vehicle. The agent utilizes reinforcement learning that uses neural networks. The agent interprets images from the front vehicle camera and selects appropriate actions to control the vehicle. I designed and created reward functions and then experimented with hyperparameters setup. Trained agent simulate driving on the road. The result of this thesis shows a possible approach to control an autonomous vehicle agent using machine learning method in CARLA simulator.
|
|
|
Deep Neural Networks for Reinforcement Learning
Ludvík, Tomáš ; Bambušek, Daniel (referee) ; Hradiš, Michal (advisor)
The aim of this thesis is to use deep neural networks for task in reinforcement learning. I use my modification of 2D game Tuxánci for the purposes of the test environment. This modification provides the possibility of using the game as an environment for machine learning. Subsequently, Iam solving the task of learning the agent by using reinforcement learning with the Double DQN algorithm.
|
|
|
Shared Experience in Reinforcement Learning
Mojžíš, Radek ; Šůstek, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this thesis is to use methods of transfer learning for training neural network on a reinforcement learning tasks. As test environment, I am using old 2D console games, such as space invaders or phoenix. I am testing the impact of re-purposing already trained models for different environments. Next I use methods for domain feature transfer. Lastly i focus on the topic of multi-task learning. From the results we can gain insight into possibilities of using transfer learning for reinforcement learning algorithms.
|
|
|
Deep Learning Methods for Machine Playing the Scotland Yard Board Game
Hrkľová, Zuzana ; Janoušek, Vladimír (referee) ; Zbořil, František (advisor)
Táto práca sa zaoberá metódami hlbokého učenia, ktoré sú aplikovateľné na stolné hry s neurčitosťou. V rámci práce boli naštudované princípy učenia s posilňovaním, s hlavným zameraním na Q-learning algoritmy, spomedzi ktorých bol vybraný Deep Q-Network algoritmus. Ten bol následne implementovaný na zjednodušených pravidlách stolnej hry Scotland Yard. Konečná implementácia bola porovnaná s metódami Alpha-Beta a Monte Carlo Tree Search. S výsledkov vyplinulo, že schovávaný hráč riadený DQN algoritmom predstavoval pre ostatné metódy najťažšieho protihráča, narozdiel od hľadajúcich hráčov, ktorým sa nepodarilo zlepšiť existujúce riešenia. Napriek tomu, že implementovaná metóda nedosiahla lepšie výsledky oproti doposiaľ existujúcim metódam, ukázalo sa, že potrebuje najmenej výpočetných zdrojov a času na vykonanie daného ťahu. To ju robí najperspektívnejšou zo spomínaných metód na budúcu možnú implementáciu originálnej verzie danej hry.
|
|
|
Deep Neural Networks for Reinforcement Learning
Ludvík, Tomáš ; Bambušek, Daniel (referee) ; Hradiš, Michal (advisor)
The aim of this thesis is to use deep neural networks for task in reinforcement learning. I use my modification of 2D game Tuxánci for the purposes of the test environment. This modification provides the possibility of using the game as an environment for machine learning. Subsequently, Iam solving the task of learning the agent by using reinforcement learning with the Double DQN algorithm.
|
|
|
Shared Experience in Reinforcement Learning
Mojžíš, Radek ; Šůstek, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this thesis is to use methods of transfer learning for training neural network on a reinforcement learning tasks. As test environment, I am using old 2D console games, such as space invaders or phoenix. I am testing the impact of re-purposing already trained models for different environments. Next I use methods for domain feature transfer. Lastly i focus on the topic of multi-task learning. From the results we can gain insight into possibilities of using transfer learning for reinforcement learning algorithms.
|
|
|
Vehicle Control via Reinforcement Learning
Maslowski, Petr ; Uhlíř, Václav (referee) ; Šůstek, Martin (advisor)
The goal of this thesis is a creation of an autonomous agent that can control a vehicle. The agent utilizes reinforcement learning that uses neural networks. The agent interprets images from the front vehicle camera and selects appropriate actions to control the vehicle. I designed and created reward functions and then experimented with hyperparameters setup. Trained agent simulate driving on the road. The result of this thesis shows a possible approach to control an autonomous vehicle agent using machine learning method in CARLA simulator.
|
|
|
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.
|
guest ::
