|
|
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.
|
|
|
Strategic Game Based on Multiagent Systems
Knapek, Petr ; Kočí, Radek (referee) ; Zbořil, František (advisor)
This thesis is focused on designing and implementing system, that adds learning and planning capabilities to agents designed for playing real-time strategy games like StarCraft. It will explain problems of controlling game entities and bots by computer and introduce some often used solutions. Based on analysis, a new system has been designed and implemented. It uses multi-agent systems to control the game, utilizes machine learning methods and is capable of overcoming oponents and adapting to new challenges.
|
|
|
Using of Reinforcement Learning for Four Legged Robot Control
Ondroušek, Vít ; Maga,, Dušan (referee) ; Maňas, Pavel (referee) ; Singule, Vladislav (referee) ; Březina, Tomáš (advisor)
The Ph.D. thesis is focused on using the reinforcement learning for four legged robot control. The main aim is to create an adaptive control system of the walking robot, which will be able to plan the walking gait through Q-learning algorithm. This aim is achieved using the design of the complex three layered architecture, which is based on the DEDS paradigm. The small set of elementary reactive behaviors forms the basis of proposed solution. The set of composite control laws is designed using simultaneous activations of these behaviors. Both types of controllers are able to operate on the plain terrain as well as on the rugged one. The model of all possible behaviors, that can be achieved using activations of mentioned controllers, is designed using an appropriate discretization of the continuous state space. This model is used by the Q-learning algorithm for finding the optimal strategies of robot control. The capabilities of the control unit are shown on solving three complex tasks: rotation of the robot, walking of the robot in the straight line and the walking on the inclined plane. These tasks are solved using the spatial dynamic simulations of the four legged robot with three degrees of freedom on each leg. Resulting walking gaits are evaluated using the quantitative standardized indicators. The video files, which show acting of elementary and composite controllers as well as the resulting walking gaits of the robot, are integral part of this thesis.
|
|
|
Reinforcement Learning for RoboCup
Bočán, Hynek ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
Goal of this thesis is creation of artificial intelligence capable of controlling robotic soccer player simulated in SimSpark environment. Agent created is expanding capabilities of existing third party agent which provides set of basic skills such as localization on the field, dribbling with the ball and omnidirectional walk. Responsibility of the created agent is to pick the best action based current state of the game. This decision making was implemented using reinforcement learning and its method Q-learning. State of the game is transformed into 2D picture with several planes. This picture is then analyzed using deep convolution neural network implemented using C++ and DeepCL library.
|
|
|
Combat Management in Starcraft II Game by Means of Artificial Intelligence
Krajíček, Karel ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
This thesis focuses on the use of Artificial Intelligence and design of working module in Real-Time Strategy (RTS) game, StarCraft II. The proposed solution uses Neural Network and Q-learning for combat management. For implementation, the StarCraft 2 Learning Environment has been used as a means of communication between the designed system and the game. Evaluation of the system is based on its ability to make progress over time.
|
|
|
Artificial Intelligence for Game Playing
Bayer, Václav ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
The focus of this work is the use of artificial intelligence methods for a playing of real-time strategic (RTS) games, where all interactions of players are performed in real time (in parallel). The thesis deals mainly with the use of machine learning method Q-learning, which is based on reinforcement learning and Markov decision process. The practice part of this work is implemented for StarCraft: Brood War game.A proposed solution learns to make up an optimal order of buildings construction in respect to a playing style (strategy) of the opponent(s). The solution is proposed within the rules of the SSCAIT tournament. Analysis and evaluation of the proposed system are based on a comparison with other participants of the competition as well as a comparison of the system behavior before and after the playing of a set of the games.
|
|
|
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.
|
|
|
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.
|
|
|
Robot path planning by means of reinforcement learning
Veselovský, Michal ; Liška, Radovan (referee) ; Dvořák, Jiří (advisor)
This thesis is dealing with path planning for autonomous robot in enviromenment with static obstacles. Thesis includes analysis of different approaches for path planning, description of methods utilizing reinforcement learning and experiments with them. Main outputs of thesis are working algorithms for path planning based on Q-learning, verifying their functionality and mutual comparison.
|
guest ::
