Wyszukiwarka
Wyniki wyszukiwania dla: reinforcement learning, dqn, logic games, prolog, wumpus world
-
Neural network agents trained by declarative programming tutors
PublikacjaThis paper presents an experimental study on the development of a neural network-based agent, trained using data generated using declarative programming. The focus of the study is the application of various agents to solve the classic logic task – The Wumpus World. The paper evaluates the effectiveness of neural-based agents across different map configurations, offering a comparative analysis to underline the strengths and limitations...
-
Model-free and Model-based Reinforcement Learning, the Intersection of Learning and Planning
PublikacjaMy doctoral dissertation is intended as the compound of four publications considering: structure and randomness in planning and reinforcement learning, continuous control with ensemble deep deterministic policy gradients, toddler-inspired active representation learning, and large-scale deep reinforcement learning costs.
-
Analysis of Learning Outcomes in Medical Education with the Use of Fuzzy Logic
PublikacjaThe national curricula of the EU member states are structured around learning outcomes, selected according to Bloom’s Taxonomy. The authors of this paper claim that using Bloom’s Taxonomy to phrase learning outcomes in medical education in terms of students’ achievements is difficult and unclear. This paper presents an efficient method of assessing course learning outcomes using Fuzzy Logic.
-
AUTOMATIC LEARNING OF STRATEGY AND RULES IN CARD GAMES USING IMAGE FROM CAMERA
PublikacjaBelow work tries to answer a question: if it is possible to replace real human with computer system in social games. As a subject for experiments, card games were chosen, because they require a lot of player interaction (playing and taking cards), while their rules are easy to present in form of clear list of statements. Such a system, should allow real players to play without constant worrying about guiding or helping computer...
-
Structure and Randomness in Planning and Reinforcement Learning
PublikacjaPlanning in large state spaces inevitably needs to balance the depth and breadth of the search. It has a crucial impact on the performance of a planner and most manage this interplay implicitly. We present a novel method \textit{Shoot Tree Search (STS)}, which makes it possible to control this trade-off more explicitly. Our algorithm can be understood as an interpolation between two celebrated search mechanisms: MCTS and random...
-
Optimizing Medical Personnel Speech Recognition Models Using Speech Synthesis and Reinforcement Learning
PublikacjaText-to-Speech synthesis (TTS) can be used to generate training data for building Automatic Speech Recognition models (ASR). Access to medical speech data is because it is sensitive data that is difficult to obtain for privacy reasons; TTS can help expand the data set. Speech can be synthesized by mimicking different accents, dialects, and speaking styles that may occur in a medical language. Reinforcement Learning (RL), in the...
-
An Empirical Study of a Dynamic Stop Loss Strategy with Deep Reinforcement Learning on the NASDAQ Stock Market
PublikacjaThe objective of this paper is to empirically investigate the efficacy of using Deep Reinforcement Learning (DRL) to maximize investment returns by incorporating expected optimal closing prices of long positions into a daily strategy. This paper extends existing research on the impact of stop-loss orders on investment strategy results and brings contribution of these orders to trading strategies into a completely new perspective....
-
Optimizing Control of Wastewater Treatment Plant With Reinforcement Learning: Technical Evaluation of Twin-Delayed Deep Deterministic Policy Gradient Agent
PublikacjaControl of the wastewater treatment processes presents significant challenges due to the fluctuating nature of inflow and wastewater composition, alongside the system’s non-linear dynamics. Traditional control methods struggle to adapt to these variations, leading to an economically suboptimal operation of the process and a violation of norms imposed on the quality of wastewater discharged to the catchment area. This study proposes...
-
Autonomous port management based AGV path planning and optimization via an ensemble reinforcement learning framework
PublikacjaThe rapid development of shipping trade pushes automated container terminals toward the direction of intelligence, safety and efficiency. In particular, the formulation of AGV scheduling tasks and the safety and stability of transportation path is an important part of port operation and management, and it is one of the basic tasks to build an intelligent port. Existing research mainly focuses on collaborative operation between...
-
The Role of Dopaminergic Genes in Probabilistic Reinforcement Learning in Schizophrenia Spectrum Disorders
Publikacja -
Confirmation Bias in the Course of Instructed Reinforcement Learning in Schizophrenia-Spectrum Disorders
Publikacja -
Alina Guzik mgr
OsobyPhD candidate at Gdańsk University of Technology Doctoral School. EdTech, digital education and innovative didactics expert, senior product manager, product designer, certified e-learning designer. Conducts scientific research in educational technology, digital education, e-learning, modern teaching methods, innovation and new product development. An author of more than a dozen award-winning EdTech products implemented in international...
-
Reinforcement Learning Algorithm and FDTD-based Simulation Applied to Schroeder Diffuser Design Optimization
PublikacjaThe aim of this paper is to propose a novel approach to the algorithmic design of Schroeder acoustic diffusers employing a deep learning optimization algorithm and a fitness function based on a computer simulation of the propagation of acoustic waves. The deep learning method employed for the research is a deep policy gradient algorithm. It is used as a tool for carrying out a sequential optimization process the goal of which is...
-
Jak wykraść złoto smokowi? - uczenie ze wzmocnieniem w świecie Wumpusa
PublikacjaNiniejszy rozdział zawiera łagodne wprowadzenie do problematyki uczenia ze wzmocnieniem, w którym podstawy teoretyczne wyjaśniane są na przykładzie przewodnim, jakim jest zagadnienie nauczenia agenta poruszania się w świecie potwora o imieniu Wumpus (ang. Wumpus world), klasycznym środowisku do testowania logicznego rozumowania agentów (problem nietrywialny dla algorytmów uczenia ze wzmocnieniem). Przedstawiona jest główna idea...
-
Workshop on Logic and Learning
Konferencje -
ANFIS-Based NPC Population Control in Video Games
PublikacjaModern computer games aim at providing rich, vivid worlds. The aim is to encourage the player to explore and interact with the in-game world. To describe the complex relations between in-game NPCs and their surrounding fuzzy logic is used. The paper presents ANFIS based population control in the video game. We present an approach allowing stabilizing the number of NPCs in-game by providing a certain amount of food to the environment....
-
Agnieszka Landowska dr hab. inż.
OsobyUkończyła studia na dwóch kierunkach: Finanse i bankowość na Uniwersytecie Gdańskim oraz Informatyka na WETI Politechniki Gdańskiej. Od 2000 roku jest związana z Politechniką Gdańską. W 2006 roku uzyskała stopień doktora w dziedzinie nauk technicznych, a w roku 2019 stopień doktora habilitowanego. Aktualnie jej praca naukowa dotyczy zagadnień interakcji człowiek-komputer oraz informatyki afektywnej (ang. affective computing), która...
-
IEEE International Symposium on Adaptive Dynamic Programming and Reinforcement Learning
Konferencje -
JamesBot - an intelligent agent playing StarCraft II
PublikacjaThe most popular method for optimizing a certain strategy based on a reward is Reinforcement Learning (RL). Lately, a big challenge for this technique are computer games such as StarCraft II which is a real-time strategy game, created by Blizzard. The main idea of this game is to fight between agents and control objects on the battlefield in order to defeat the enemy. This work concerns creating an autonomous bot using reinforced...
-
Possible uses of crisis situation aiding system in virtual world simulation
PublikacjaMany of the real world crisis situations like spreading fire, hostile units attack, flood, and etc. are commonly used in computer games where a simulation of extensive virtual world is crucial. This paper presents some ideas for possible uses of existing crisis situation aiding system in such environments. Moreover it shows how this kind of system can be taught during subsequent games with a large number of players.
-
Software Factory project for enhancement of student experiential learning
PublikacjaProviding opportunities for students to work on real-world software development projects for real customers is critical to prepare students for the IT industry. Such projects help students to understand what they will face in the industry and experience real customer interaction and challenges in collaborative work. To provide this opportunity in an academic environment and enhance the learning and multicultural teamwork experience,...
-
Possible uses of crisis situation aiding system in virtual world simulation
PublikacjaMany of the real world crisis situations like spreading fire, hostile units attack, flood, and etc. are commonly used in computer games where a simulation of extensive virtual world is crucial. This paper presents some ideas for possible uses of existing crisis situation aiding system in such environments. Moreover, it shows how this kind of system can be taught during subsequent games with a large number of players. As an example...
-
Hossein Nejatbakhsh Esfahani Dr.
OsobyMy research interests lie primarily in the area of Learning-based Safety-Critical Control Systems, for which I leverage the following concepts and tools:-Robust/Optimal Control-Reinforcement Learning-Model Predictive Control-Data-Driven Control-Control Barrier Function-Risk-Averse Controland with applications to:-Aerial and Marine robotics (fixed-wing UAVs, autonomous ships and underwater vehicles)-Multi-Robot and Networked Control...
-
Designing effective educational games - a case study of a project management game
PublikacjaThis paper addresses the issues of designing effective educational games. We aim at investigating how the cognitive, behavioral and emotional aspects of the games influence their educational effectiveness. The results were obtained with an observational user experience study extended with affect analysis carried out for a project management game GraPM. We analyzed the...
-
Ontologies vs. Rules — Comparison of Methods of Knowledge Representation Based on the Example of IT Services Management
PublikacjaThis text provides a brief overview of selected structures aimed at knowledge representation in the form of ontologies based on description logic and aims at comparing them with their counterparts based on the rule-based approach. Due to the limitations on the length of the article, only elements associated with the representation of concepts could be shown, without including roles. The formalisms of the OWL language were used...
-
Aleksandra Teresa Wiśniewska dr inż.
Osobyeducation Postgraduate studies in “ Scandinavian Studies“ University of Gdańsk (2019-2020), Postgraduate studies in "Research Project Management and Commercialization of Research Results" Gdańsk University of Technology, Faculty of Management and Economics (2010–2011), Postgraduate studies "Control & Management of Lean Manufacturing in Network Systems", Fachhochschule Karlsruhe (1998–2000), Master's studies "Automation...
-
Muhammad Usman PhD
OsobyMuhammad Usman is currently a Computer Vision Researcher at Gdansk University of Technology, working on the BE-LIGHT project, where his research focuses on advancing biomedical diagnostics through the integration of light-based technologies and machine learning techniques. He has completed his Master’s degree in Control Science and Engineering from the University of Science and Technology of China (USTC), Hefei, China. His research...
-
Zastosowanie komputerów w dziedzinie wyszukiwania strategii optymalnych w grach logicznych
PublikacjaProblem jaki stanowi wyszukiwanie strategii optymalnej w grach logicznych jest bardzo złożony. Można go podzielić na następujące podproblemy: obliczeniowy, pamięciowy oraz operacji wejścia/wyjścia. Jednak rosnąca z roku na rok siła obliczeniowa komputerów, ilość pamięci oraz prędkość transferu danych pomiędzy podzespołami zarówno lokalnymi jak i rozproszonymi, a także wzrost skuteczności wykorzystywanych technik algorytmicznych...
-
Designing acoustic scattering elements using machine learning methods
PublikacjaIn the process of the design and correction of room acoustic properties, it is often necessary to select the appropriate type of acoustic treatment devices and make decisions regarding their size, geometry, and location of the devices inside the room under the treatment process. The goal of this doctoral dissertation is to develop and validate a mathematical model that allows predicting the effects of the application of the scattering...
-
Game-based Sprint retrospectives: multiple action research
PublikacjaIn today’s fast-paced world of rapid technological change, software development teams need to constantly revise their work practices. Not surprisingly, regular reflection on how to become more effective is perceived as one of the most important principles of Agile Software Development. Nevertheless, running an effective and enjoyable retrospective meeting is still a challenge in real environments. As reported by several studies,...
-
IMPACT OF THE ORGANISATION OF MEGA SPORTING EVENTS ON SELECTED ELEMENTS OF THE TOURISM SECTOR
PublikacjaIntroduction. In the world-wide literature, there is no unanimity in the assessment of the impact of mega sporting events on the tourism sector. Therefore, the main purpose of this study was to quantify the impact of mega sporting events on changes in tourist inflow and the amount of expenditure incurred by visitors. Material and methods. In this study, an ex-post analysis of many different categories of mega sporting events was...
-
Fashion Games, Fashion in Games and Gamification in Fashion. A First Map
PublikacjaFashion companies have been using different forms of entertainment such as film and television, sport, music, museums, and photography as inspiration sources and as communication and marketing channels for decades. However, in recent years, they have also started to consider the gaming world. While gaming offers a potential revenue stream from sales of physical and digital clothing, change in it is also the gateway to access new...
-
Application of artificial intelligence into/for control of flexible manufacturing cell
PublikacjaThe application of artificial intelligence in technological processes control is usually limited. One problem is how to respond to changes in the environment of manufacturing system. A way to overcome the above shortcoming is to use fuzzy logic for representation of the inexact information. In this paper fundamentals of artificial intelligence and fuzzy logic are introduced from a theoretical point of view. Still more the fuzzy...
-
Ontology-Aided Software Engineering
PublikacjaThis thesis is located between the fields of research on Artificial Intelligence (AI), Knowledge Representation and Reasoning (KRR), Computer-Aided Software Engineering (CASE) and Model Driven Engineering (MDE). The modern offspring of KRR - Description Logic (DL) [Baad03] is considered here as a formalization of the software engineering Methods & Tools. The bridge between the world of formal specification (governed by the mathematics)...
-
Predicting bankruptcy with the use of macroeconomic variables
PublikacjaRegarding the current global financial crisis, the firms can expect the increased uncertainty of their existence. The relevant literature includes extensive studies on bankruptcy prediction. Studies show that the most popular method used for prediction of firms' failures are discriminant analyses (30,3% of all models), then logit and probit models (21,3%), which all three are parametric models. The nature, the structure of the...
-
Ontologie vs. reguły — porównanie metod reprezentacji wiedzy na przykładzie dziedziny zarządzania usługami informatycznymi
PublikacjaTekst stanowi krótki przegląd wybranych konstrukcji służących reprezentacji wiedzy w postaci ontologii opartych na logice opisowej i porównanie ich z odpowiednikami opartymi na zapisie regułowym. Z powodu ograniczonej liczby stron pokazano tylko elementy związane z reprezentacją konceptów, bez uwzględniania ról. Do zapisu ontologii wykorzystano formalizmy języka OWL, zaś reguły wyrażono w Prologu. Dla lepszego zilustrowania tych...
-
Lifelong Learning Idea in Architectural Education
PublikacjaThe recent advances in IT and technology are forcing changes in the approach to educating society. In the 20th century, life-long learning was understood as educating adults in order to improve their occupational qualifications. Life-long learning allows the needs of the present-day world to be addressed through providing the individual with education at every stage of his/her life various forms. The search for a new model...
-
Applying Fuzzy Logic of Expert Knowledge for Accurate Predictive Algorithms of Customer Traffic Flows in Theme Parks
PublikacjaThis study analyzes two forecasting models based on the application of fuzzy logic and evaluates their effectiveness in predicting visitor expenditure and length of stay at a popular theme park. The forecasting models are based on a set of more than 600 decision rules constructed in the form of a complex series of IF-THEN statements. These algorithms store expert knowledge. A descriptive instrument that records the individual visitor's...
-
Chain Action - How Do Countries Add Value Through Digital Government?
PublikacjaThis study examineshow countries develop and benefit from Digital Government(DG).The literature proposes various conceptualizations of the value-adding logic of DG, but the benchmarking practice is not respondingto such proposals.For instance, the United Nations’E-Government Surveycombines the readiness and uptake indicatorsand failsto cover any impactindicators;thus,its diagnostic valueis limited. To overcome...
-
Big Data from Sensor Network via Internet of Things to Edge Deep Learning for Smart City
PublikacjaData from a physical world is sampled by sensor networks, and then streams of Big Data are sent to cloud hosts to support decision making by deep learning software. In a smart city, some tasks may be assigned to smart devices of the Internet of Things for performing edge computing. Besides, a part of workload of calculations can be transferred to the cloud hosts. This paper proposes benchmarks for division tasks between an edge...
-
Contra Bellum: Bell's Theorem as a Confusion of Languages
PublikacjaBell's theorem is a conflict of mathematical predictions formulated within an infinite hierarchy of mathematical models. Inequalities formulated at level k ∈ Z are violated by probabilities at level k+1. We are inclined to think that k=0 corresponds to the classical world, while k=1 — to the quantum one. However, as the k=0 inequalities are violated by k=1 probabilities, the same relation holds between k=1 inequalities violated...
-
NOWE TRENDY I KIERUNKI BADAŃ W MARKETINGU USŁUG
PublikacjaOd momentu pojawienia się koncepcji marketingu usług przechodzi ona nieustającą ewolucję. Pojawiające się nowe trendy (m.in. Service-Dominant Logic, Service Logic, New Service Marketing) i obszary badań marketingu usług (np. Transformative Service Research) skłaniają do dokonywania podsumowań pewnego etapu rozwoju i stawiania pytań, w którym kierunku powinny podążać badania marketingu usług w przyszłości. Celem artykułu jest przedstawienie...
-
Herbarium of Division of Marine Biology and Ecology University of Gdańsk (DMBE)
Dane BadawczeHerbarium of Division of Marine Biology and Ecology University of Gdańsk (DMBE) is a research herbarium encompassing specimens of vascular plants and algae hosted by the Laboratory of Marine Plant Ecology at University of Gdańsk, Poland. The aim of Herbarium is to preserve marine plant and algae collections mostly from the Gulf of Gdańsk, but the herbarium...
-
Wielkie wydarzenia jako katalizator procesów rewitalizacji
PublikacjaCelem referatu jest naświetlenie procesów rewitalizacji towarzyszących organizacji wielkich wydarzeń w dwóch aspektach: 1) rewitalizacja jako motor lub jako skutek działań; 2) lokalność i regionalność procesów rewitalizacji. Omówieniu tych zjawisk służą przykłady miast-organizatorów wielkich wydarzeń, Sydney (IO 2000), Pekin (IO 2008), Londyn (IO 2012) oraz Gdańsk (Euro 2012) i Szczecin (The Tall Ships Races 2013). Kluczową kwestią...
-
How Machine Learning Contributes to Solve Acoustical Problems
PublikacjaMachine learning is the process of learning functional relationships between measured signals (called percepts in the artificial intelligence literature) and some output of interest. In some cases, we wish to learn very specific relationships from signals such as identifying the language of a speaker (e.g. Zissman, 1996) which has direct applications such as in call center routing or performing a music information retrieval task...
-
Analysis of Factors Influencing the Prices of Tourist Offers
PublikacjaTourism is a significant branch of many world economies. Many factors influence the volume of tourist traffic and the prices of trips. There are factors that clearly affect tourism, such as COVID-19. The paper describes the methods of machine learning and process mining that allow for assessing the impact of various factors (micro, mezzo and macro) on the prices of tourist offers. The methods were used on large sets of real data...
-
Fuzzy Gaussian Decision Tree
PublikacjaThe Decision Tree algorithm is one of the first machine learning algorithms developed. It is used both as a standalone model and as an ensemble of many cooperating trees like Random Forest, AdaBoost, Gradient Boosted Trees, or XGBoost. In this work, a new version of the Decision Tree was developed for classifying real-world signals using Gaussian distribution functions and a fuzzy decision process. The research was carried out...
-
Study on Strategy in University Laboratory Class Teaching
PublikacjaLaboratory teaching is a critical way to ensure the effective input of techniques in engineering learning. Laboratory teaching not only contributes to improving course quality but also helps enrich comprehensive engineering application ability. However, there are some typical problems in current university laboratory teaching, such as rigid and isolated course design, outdated contents and materials, and not encouraging innovation...
-
Designing learning spaces through international and interdisciplinary collaborative design studio: The case of engineer architects and pedagogic students
PublikacjaThe study explores the dynamics and outcomes of an international interdisciplinary design studio focusing on innovative learning spaces. Conducted over two years between students of Faculty of Architecture at Gdansk Tech and pedagogic students from Kibbutzim College in Tel Aviv, this design-based study examines the contributions of unique educational program to student learning, the evolution of the design process, collaboration,...
-
Piotr Figura dr inż.
OsobyPiotr Figura jest pracownikiem Katedry Finansów na Wydziale Zarządzania i Ekonomii Politechniki Gdańskiej, a także członkiem Komisji Wydziałowej ds. Weryfikacji Efektów Uczenia się oraz recenzentem akademickim zadań z zakresu rachunkowości Centralnej Komisji Edukacyjnej. Jest autorem lub współautorem kilku monografii naukowych w tym: Wartości wzorcowe wskaźników finansowych przedsiębiorstw giełdowych; Classical and modern concepts...