|
|
Playing Games Using Neural Networks
Buchal, Petr ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this bachelor thesis is to teach a neural network solving classic control theory problems and playing the turn-based game 2048 and several Atari games. It is about the process of the reinforcement learning. I used the Deep Q-learning reinforcement learning algorithm which uses a neural networks. In order to improve a learning efficiency, I enriched the algorithm with several improvements. The enhancements include the addition of a target network, DDQN, dueling neural network architecture and priority experience replay memory. The experiments with classic control theory problems found out that the learning efficiency is most increased by adding a target network. In the game environments, the Deep Q-learning has achieved several times better results than a random player. The results and their analysis can be used for an insight to reinforcement learning algorithms using neural networks and to improve the used techniques.
|
|
|
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.
|
|
|
Simulation-Based Development of Heating Control System
Tomeček, Jan ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
This thesis is about optimalization of boiler heating from external sources. I have created a simulation model of Heating Control System. Subsequently, using a simulation model, I proposed possible optimizations for water heating control. The used optimization method was deep Q-learning. The result of this work shows the use of simulation for the development and optimalization of control systems.
|
|
|
Simulation-Based Development of Heating Control System
Tomeček, Jan ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
This thesis is about optimalization of boiler heating from external sources. I have created a simulation model of Heating Control System. Subsequently, using a simulation model, I proposed possible optimizations for water heating control. The used optimization method was deep Q-learning. The result of this work shows the use of simulation for the development and optimalization of control systems.
|
|
|
Artificial Intelligence for the Santorini Board Game
Rybanský, Adam ; Kocour, Martin (referee) ; Beneš, Karel (advisor)
The aim of this thesis was to use create an intelligent agent using Reinforcement learning to play Santorini, a 2-player zero-sum board game. The specific algorithm that was implemented was a modified version of Deep Q-learning, with the use of convolutional neural networks (one for training and the other for estimating future Q-value) and a memory of previously executed moves, from which the agent chooses randomly during training. Numerous experiments resulted in 2 final models. One was trained by playing against basic bots, with gradually increasing difficulty. The other was trained by playing against itself from the start. The outcome shows that the model playing against itself produces better results, however both models still perform worse than a bot which uses heuristic function.
|
|
|
Simulation-Based Development of Heating Control System
Tomeček, Jan ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
This thesis is about optimalization of boiler heating from external sources. I have created a simulation model of Heating Control System. Subsequently, using a simulation model, I proposed possible optimizations for water heating control. The used optimization method was deep Q-learning. The result of this work shows the use of simulation for the development and optimalization of control systems.
|
|
|
Simulation-Based Development of Heating Control System
Tomeček, Jan ; Rozman, Jaroslav (referee) ; Janoušek, Vladimír (advisor)
This thesis is about optimalization of boiler heating from external sources. I have created a simulation model of Heating Control System. Subsequently, using a simulation model, I proposed possible optimizations for water heating control. The used optimization method was deep Q-learning. The result of this work shows the use of simulation for the development and optimalization of control systems.
|
|
|
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.
|
|
|
Space game with artificial intelligence
Bašta, Přemysl ; Pilát, Martin (advisor) ; Gemrot, Jakub (referee)
Part of this thesis consists of the implementation of my own simple space game which serves as an experimenting en vironment for testing different aproaches of artificial inteligence. There have been created abstractions in a form of sensoric methods and action plans as a transition between low leve l and high level information about game state and actions. These abstractions help algorithms of artifical inteligence with game agent manipulation. As far as algorithms are considered I chose genetic programming and Deep Q-learning as main aproachces for inteli gent agent development. Final part contains description of behaviour of developed agents and discussion of performed experiments.
|
|
|
Playing Games Using Neural Networks
Buchal, Petr ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this bachelor thesis is to teach a neural network solving classic control theory problems and playing the turn-based game 2048 and several Atari games. It is about the process of the reinforcement learning. I used the Deep Q-learning reinforcement learning algorithm which uses a neural networks. In order to improve a learning efficiency, I enriched the algorithm with several improvements. The enhancements include the addition of a target network, DDQN, dueling neural network architecture and priority experience replay memory. The experiments with classic control theory problems found out that the learning efficiency is most increased by adding a target network. In the game environments, the Deep Q-learning has achieved several times better results than a random player. The results and their analysis can be used for an insight to reinforcement learning algorithms using neural networks and to improve the used techniques.
|
guest ::
