|
|
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.
|
|
|
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.
|
|
|
Artificial intelligence for real-time strategic games
Sýkora, Ondřej
Title: Artificial intelligence for real-time strategic games Author: Ondřej Sýkora Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: Mgr. Cyril Brom Supervisor's e-mail address: brom@ksvi.mff.cuni.cz Abstract: Among the computer game players, real-time strategy games (RTS) are one of the most popular genres. Despite of this fact, there is a very low number of publicati- ons concerning this genre. In this thesis we study the problem of an action selection in the real-time strategy games using methods based on Markov decision processes. In the first chapters we introduce the genre of real-time strategy games from the game designer's perspective as well as from the view of an artificial intelligence researcher. We give an introduction to the Markov decision processes and to methods designed to solve them. We propose a solution of the problem of an action selection based on Markov decision problem solving using a discrete-event simulation of the real-time strategy game. We test the clarity of the proposed method and its properties. Keywords: real-time strategy game, Markov decision process, Expected Outcome, bandit- based planning, discrete-event-simulation 6
|
|
|
Mixing of Predictors in Parameter Estimation
Podlesna, Yana ; Kárný, Miroslav
This bachelor thesis deals with the design of the method for solving the curse of dimensionality arising in the quantitative modeling of complex interconnected systems. The employed predictive models are based on a discrete Markov process. Prediction is based on estimating model parameters using Bayesian statistics. This work contains method for reducing the amount of data needed for prediction in systems with a large number of occurring states and actions. Instead of estimating a predictor dependent on all parameters, the method assumes the use of several predictors, which arise from estimating parametric models based on dependences on different regressors. The behavioral properties of the proposed method are illustrated by simulation experiments.
|
|
| |
|
|
Artificial intelligence for real-time strategic games
Sýkora, Ondřej
Title: Artificial intelligence for real-time strategic games Author: Ondřej Sýkora Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: Mgr. Cyril Brom Supervisor's e-mail address: brom@ksvi.mff.cuni.cz Abstract: Among the computer game players, real-time strategy games (RTS) are one of the most popular genres. Despite of this fact, there is a very low number of publicati- ons concerning this genre. In this thesis we study the problem of an action selection in the real-time strategy games using methods based on Markov decision processes. In the first chapters we introduce the genre of real-time strategy games from the game designer's perspective as well as from the view of an artificial intelligence researcher. We give an introduction to the Markov decision processes and to methods designed to solve them. We propose a solution of the problem of an action selection based on Markov decision problem solving using a discrete-event simulation of the real-time strategy game. We test the clarity of the proposed method and its properties. Keywords: real-time strategy game, Markov decision process, Expected Outcome, bandit- based planning, discrete-event-simulation 6
|
guest ::
