National Repository of Grey Literature 3 records found  Search took 0.01 seconds. 
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.
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.
Risk management methods within the banking institution's test environment
Mádl, Jiří ; Bruckner, Tomáš (advisor) ; Mandera, Petr (referee)
In the presented bachelor thesis I focus on methods of risk management within the hypothetical banking institution's test environment. Risk management includes data anonymization and the creation of the test environment to offer the most faithful copy of the production environment. In the theoretical part I deal with the theory of data anonymization, the legislative framework of the Czech Republic and the European Union, the theory of testing and define the theoretical production environment of a hypothetical banking institution that is based on the real environment of ČSOB Leasing a.s.. I subsequently propose and analyze possible solutions to create a test environment. The aim of this analysis is to choose the most appropriate way of creating a test environment, which is applied in a practical part to a hypothetical environment. The practical part is also devoted to the governance of the proposed process.

Interested in being notified about new results for this query?
Subscribe to the RSS feed.