|
|
Acquisition of Costly Information in Data-Driven Decision Making
Janásek, Lukáš ; Baruník, Jozef (advisor) ; Vácha, Lukáš (referee)
This thesis formulates and solves an economic decision problem of the acquisi- tion of costly information in data-driven decision making. The thesis assumes an agent predicting a random variable utilizing several costly explanatory vari- ables. Prior to the decision making, the agent learns about the relationship between the random variables utilizing its past realizations. During the deci- sion making, the agent decides what costly variables to acquire and predicts using the acquired variables. The agent's utility consists of the correctness of the prediction and the costs of the acquired variables. To solve the decision problem, the thesis divides the decision process into two parts: acquisition of variables and prediction using the acquired variables. For the prediction, the thesis presents a novel approach for training a single predictive model accepting any combination of acquired variables. For the acquisition, the thesis presents two novel methods using supervised machine learning models: a backward es- timation of the expected utility of each variable and a greedy acquisition of variables based on a myopic increase in the expected utility of variables. Next, the thesis formulates the decision problem as a Markov decision process which allows approximating the optimal acquisition via deep...
|
|
|
Utilization of Robotic Operating System (ROS) for control of collaborative robot UR3
Juříček, Martin ; Matoušek, Radomil (referee) ; Parák, Roman (advisor)
The aim of the bachelor's thesis is to create a control program, its subsequent testing and verification of functionality for the collaborative robot UR3 from the company Universal Robots. The control program is written in python and integrates control options through the Robotic Operating System, where a defined point can be reached using pre-simulated trajectories of Q-learning, SARSA, Deep Q-learning, Deep SARSA, or using only the MoveIT framework. The thesis deals with a cross-section of the topics of collaborative robotics, Robotic Operating System, Gazebo simulation environment, feedback and deep feedback learning. Finally, the design and implementation of the control program with partial parts is described.
|
|
|
Settlers of Catan
Novák, Daniel ; Hric, Jan (advisor) ; Pilát, Martin (referee)
In this thesis, we work on implementation of the board game Settlers of Ca- tan and artifitial intelligence playing this game. The artificial intelligence is based on a combination of expectimax and reinforcement learning. Using reinforcement learning, we have been able to develop an agent who can play reasonably. We ma- naged to improve the policy learned by reinforcement learning using expectimax. The resulting agent is able to win aganist average human player.
|
|
|
Navigation Using Deep Convolutional Networks
Skácel, Dalibor ; Veľas, Martin (referee) ; Hradiš, Michal (advisor)
This thesis studies navigation and autonomous driving using convolutional neural networks. It presents main approaches to this problem used in literature. It describes theory of neural networks and imitation and reinforcement learning. It also describes tools and methods suitable for a driving system. There are two simulation driving models created using learning algorithms DAGGER and DDPG. The models are then tested in car racing simulator TORCS.
|
|
|
Reinforcement Learning for 3D Games
Beránek, Michal ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
Thesis deals with neural network learning on simple tasks in 3D shooter Doom, mediated by research platform ViZDoom. The main goal is to create an agent, which is able to learn multiple tasks simultaneously. Reinforcement learning algorithm used to achieve this goal is called Rainbow, which combines several improvements of DQN algorithm. I proposed and experimented with two different architectures of neural network for learning multiple tasks. One of them was successful and after a relatively short period of learning it reached almost 50% of maximum possible reward. The key element of this achievement is an Embedding layer for parametric description of task environment. The main discovery is, that Rainbow is able to learn in 3D environment and with the help of Embedding layer, it is able to learn on multiple tasks simultaneously.
|
|
|
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.
|
|
|
Navigation Using Deep Convolutional Networks
Skácel, Dalibor ; Veľas, Martin (referee) ; Hradiš, Michal (advisor)
In this thesis I deal with the problem of navigation and autonomous driving using convolutional neural networks. I focus on the main approaches utilizing sensory inputs described in literature and the theory of neural networks, imitation and reinforcement learning. I also discuss the tools and methods applicable to driving systems. I created two deep learning models for autonomous driving in simulated environment. These models use the Dataset Aggregation and Deep Deterministic Policy Gradient algorithms. I tested the created models in the TORCS car racing simulator and compared the result with available sources.
|
|
|
Extending Hotelling's location model into Agent-based domain
Vainer, Jan ; Kukačka, Jiří (advisor) ; Smutná, Šarlota (referee)
This thesis examines behaviour of adaptive agents in Hotelling's location model. We conduct an agent-based simulation in Hotelling's setting with two agents, where the agents use Nash-Q learning mechanism for adaptation. Traditional game-theoretic models often stand on strong assumptions imposed on players such as rationality and perfect information. We explore what alternations or re- finements of results this technique brings in comparison to the original analytical solution of the theoretical Hotelling's location model. We discover that under Nash-Q learning and quadratic consumer cost func- tion, agents with high enough valuation of future profits learn behaviour similar to aggressive market strategy, where both agents make similar products and lead a price war in order to eliminate their opponent from the market. This be- haviour closely resembles the Minimum differentiation principle from the original Hotelling's paper with linear consumer costs. This result is surprising because in our simulation, quadratic consumer cost functions are used, which should result in maximum differentiation of the products. Our results suggest that the Prin- ciple of minimum differentiation could be justified based on repeated interaction of the agents and long-run optimization. Additionally, suitability of...
|
|
|
Reinforcement learning for solving game algorithms
Daňhelová, Jana ; Uher, Václav (referee) ; Kolařík, Martin (advisor)
The bachelor thesis Reinforcement learning for solving game algorithms is divided into two distinct parts. The theoretical part describes and compares the fundamental methods of reinforcement learning with special attention to the methods of active learning – Q-learning and deep learning. In the practical part the deep q-learning technique is chosen for testing and applied to the case of the Snake game. The results are presented in the form of program written in Python programming language, which consists of the game environment created in PyGame, the model of convolutional neural network designed in Keras and agent playing the game. As an output of the program there are several types of datasets in CSV format. The gained data containing the values of parameters like number of epochs, accuracy, loss or the amount of the reward can later be used for further processing.
|
|
|
Using reinforcement learning to learn how to play text-based games
Zelinka, Mikuláš ; Kadlec, Rudolf (advisor) ; Lisý, Viliam (referee)
The ability to learn optimal control policies in systems where action space is defined by sentences in natural language would allow many interesting real-world applications such as automatic optimisation of dialogue systems. Text-based games with multiple endings and rewards are a promising platform for this task, since their feedback allows us to employ reinforcement learning techniques to jointly learn text representations and control policies. We present a general text game playing agent, testing its generalisation and transfer learning performance and showing its ability to play multiple games at once. We also present pyfiction, an open-source library for universal access to different text games that could, together with our agent that implements its interface, serve as a baseline for future research.
|
guest ::
