|
|
Search in Imperfect Information Games
Schmid, Martin ; Hladík, Milan (advisor) ; Szepesvari, Csaba (referee) ; Bošanský, Branislav (referee)
From the very dawn of the field, search with value functions was a fun- damental concept of computer games research. Turing's chess algorithm from 1950 was able to think two moves ahead, and Shannon's work on chess from 1950 includes an extensive section on evaluation functions to be used within a search. Samuel's checkers program from 1959 already combines search and value functions that are learned through self-play and bootstrapping. TD-Gammon improves upon those ideas and uses neural networks to learn those complex value functions - only to be again used within search. The combination of decision-time search and value functions has been present in the remarkable milestones where computers bested their human counterparts in long standing challenging games - DeepBlue for Chess and AlphaGo for Go. Until recently, this powerful framework of search aided with (learned) value functions has been limited to perfect information games. As many interesting problems do not provide the agent perfect information of the environment, this was an unfortunate limitation. This thesis introduces the reader to sound search for imperfect information games. 1
|
|
|
Game theory and poker
Schmid, Martin ; Hladík, Milan (advisor) ; Zimmermann, Karel (referee)
This thesis introduces the basic concepts of the game theory. Necessary models and solution concepts are described. Follows the summary of the computational complexity of these concepts and corresponding algorithms. Poker is formalized as one of the game theory game models. State of the art algorithms for the ex- tensive form games are explained with the application to the Poker. The thesis also introduces the Annual Computer Poker Competition and participating pro- grams. Finally, new result about the extensive form games with many actions is presented. Keywords: Game theory, Poker, Nash equilibrium, Extensive form games
|
|
|
Opponent Modelling in Games with Imperfect Information
Kovačič, Milan ; Schmid, Martin (advisor) ; Hartman, David (referee)
The main concern of this paper is the problem of opponent modeling. The goal of this work is to introduce reasonable selection of techniques, which model the opponent's behavior and use it in effective way. In this work I focused on explanation of fundamental terms, introduction of relevant techniques and safety of opponent modeling considering the game of poker. The research showed that effective opponent modeling is indeed possible with reasonable safety and surprising effectivity in comparison with pessimistic equilibrium techniques.
|
|
|
Convolutional neural networks and their implementation
Schmid, Martin ; Mrázová, Iveta (advisor) ; Petříčková, Zuzana (referee)
Bachelor thesis describes using convolutional neural networks for recognizing symbols from images. First describes this model and shows it's implementation. Then this implementation is used for sample application. First, model of neural networks is described, then learning of this model (including backpropagation algorithm). Finally, convolutional neural networks are presented with it's advantages for symbol recognition. Then some existing implementations of neural networks are analyzed, including speed comparison. None of these implementations support convolutional networks, so this model is added to one of them. Then this extension and it's interface (how to use it) is presented. To show features of this model and to prove functionality of the implementation, sample application is created. This application is available on the web site and runnable using only a web browser. Keywords: Convolutional neural networks, OCR, Encog 7
|
|
|
Opponent Modelling in Games with Imperfect Information
Kovačič, Milan ; Schmid, Martin (advisor) ; Hartman, David (referee)
The main concern of this paper is the problem of opponent modeling. The goal of this work is to introduce reasonable selection of techniques, which model the opponent's behavior and use it in effective way. In this work I focused on explanation of fundamental terms, introduction of relevant techniques and safety of opponent modeling considering the game of poker. The research showed that effective opponent modeling is indeed possible with reasonable safety and surprising effectivity in comparison with pessimistic equilibrium techniques.
|
|
|
Game theory and poker
Schmid, Martin ; Hladík, Milan (advisor) ; Zimmermann, Karel (referee)
This thesis introduces the basic concepts of the game theory. Necessary models and solution concepts are described. Follows the summary of the computational complexity of these concepts and corresponding algorithms. Poker is formalized as one of the game theory game models. State of the art algorithms for the ex- tensive form games are explained with the application to the Poker. The thesis also introduces the Annual Computer Poker Competition and participating pro- grams. Finally, new result about the extensive form games with many actions is presented. Keywords: Game theory, Poker, Nash equilibrium, Extensive form games
|
|
|
Convolutional neural networks and their implementation
Schmid, Martin ; Mrázová, Iveta (advisor) ; Petříčková, Zuzana (referee)
Bachelor thesis describes using convolutional neural networks for recognizing symbols from images. First describes this model and shows it's implementation. Then this implementation is used for sample application. First, model of neural networks is described, then learning of this model (including backpropagation algorithm). Finally, convolutional neural networks are presented with it's advantages for symbol recognition. Then some existing implementations of neural networks are analyzed, including speed comparison. None of these implementations support convolutional networks, so this model is added to one of them. Then this extension and it's interface (how to use it) is presented. To show features of this model and to prove functionality of the implementation, sample application is created. This application is available on the web site and runnable using only a web browser. Keywords: Convolutional neural networks, OCR, Encog 7
|
guest ::
RSS feed.