Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 23 for “"deep Q-network"”.
-
Creation of a Cognitive Radar with Machine Learning: Simulation and Implementation
… a Markov Decision Process (MDP), and then apply Deep-Q Learning to optimize radar performance. The radar environment includes a single point target and a communications system that will potentially interfere with the radar. We demonstrate that the Deep-Q Network (DQN) we construct is able to …
-
Improving information extraction by acquiring external evidence with reinforcement learning
… based on contextual information. We employ a deep Q-network, trained to optimize a reward function that reflects extraction accuracy while penalizing extra effort. Our experiments on two databases - of shooting incidents, and food adulteration cases - demonstrate that our system significantly …
-
Spectrum Management in Dynamic Spectrum Access: A Deep Reinforcement Learning Approach
… there is no powerful infrastructure in DSA networks to support centralized control. As a result, DSA users have to perform spectrum managements, including spectrum access and power allocations, independently without accurate channel state information. In this thesis, a novel spectrum …
-
Enabling rApp in 5G O-RAN: An Spectral Optimization (SO)rApp Use Case
… Learning (RL) techniques, specifically a Deep Q-Network (DQN) model, within the O-RAN architecture. The research highlights how the SOrApp dynamically allocates spectrum resources to enhance network performance under varying demand conditions. Utilizing the Network Simulator (NS)-3 5G-LENA …
-
Optimizing COVID-19 control measures using multi-objective deep reinforcement learning
… measures through the use of multi-objective deep re- inforcement learning techniques. The results of two case studies, one using a Pareto conditioned network on COVID-19 data from Belgium and the other using a Deep Q-Network, Goal-DQN, and Non-dominated Sorting Genetic Algorithm (NSGA-II) on …
-
Training and Inference in Early-Exit Deep Q-Networks for Efficient Reinforcement Learning
Neural networks have become instrumental in various machine learning tasks, but their increasing complexity poses challenges in terms of computational resources and real-time decision-making. To address these challenges, this thesis explores the integration of early-exit neural networks (EENNs) …
-
WhatWhen2Ask: Cost-Aware LLM Querying for Autonomous Robots in Uncertain Environments
… language models (MLLMs). The agent employs a Deep Q-Network (DQN) as its internal action planner, selectively querying open- and closed-source models (BLIP-2 and GPT-4o) in a hierarchical manner when its confidence is low and external guidance is likely to improve performance. Accepted hints …
-
Performance of an AGI-aspiring system & narrow-AI approaches : a systematic comparison
… identical to those previously tested on a double deep Q network (DDQ) and an actor-critic (AC). ONA was found to vastly outperform the narrow-AI learners in proficiency and learning speed, but could not handle one variable being random or its actions being swapped. The results indicate that the …
-
Human-Aware AI-Assistant
… Six supervised learning methods and two Deep Q Network structures are trained and analyzed to find the best models for the AI-assistant’s planning and inference systems. The results of training and testing different methods suggest using the DQN models as planners for simple scenarios …
-
Enabling Experimentation and Evaluation of xApp Direct Conflict Detection and Mitigation in Testbed
Telecommunications networks have evolved from enabling human-focused communication to supporting machine-driven interactions such as Internet of Things (IoT) communication. This shift demands increasingly intelligent and adaptive infrastructures, most notably through the virtualization of the Radio …
-
Optimal energy management for a grid-tied solar PV-battery microgrid: A reinforcement learning approach
… power plants and toward a decentralized network based on renewables. Microgrids, either grid-connected or islanded, provide a key solution for integrating RERs, load demand flexibility, and energy storage systems within this framework. Nonetheless, renewable energy resources, such as …
-
Improving network pavement performance management using machine learning
Highway networks play a significant role in people’s daily life. With limited funding and increasing demand, it is critical for transportation agencies to maintain the condition of the highway network cost-effectively. This necessitates the development of sound network pavement performance models …
-
Dynamic Defense for Adaptive Resilience Against Emerging Threats in Microgrid Cybersecurity Games
… rely on embedded devices and communication networks to achieve controllability. The interdependence of physical and cyber layers in such systems makes them vulnerable to process-level rootkit attacks that can manipulate system states to hinder the achievement of nominal functionality, …
-
Enhancing Molecular Docking with Deep Q-Networks
… aprovechar los prometedores algoritmos de Deep RL para mejorar la resolución del problema de Docking. Para ello, el hilo conductor de esta tesis doctoral son las diferentes alternativas de representación de las moléculas de la escena de Docking que serán utilizadas como datos de entrada de …
-
Data-Driven Routing for Autonomous Trucks: Learning from Human Behavior with Context Awareness and Privacy Protection
… first objective introduces the Multi-Intention Deep Inverse Reinforcement Learning (MIDIRL) framework for reconstructing truck trajectories from low-frequency GPS data. MIDIRL models diverse driver preferences by learning reward functions from high-frequency trajectories and identifying …
-
Efficient radio resource management in integrated terrestrial and non-terrestrial networks
The beyond 5G (B5G) networks are envisaged to provide terra bps data rates and ubiquitous and unlimited wireless coverage. However, the terrestrial deployment of 5G networks poses a limitation in achieving a truly ubiquitous and seamlessly connected network. To this end, it has been proposed to …
-
Intelligent and Dynamic Spectrum Management for Beyond 5G
The 5G network introduces virtualisation technology and network slicing, that allows an agile creation and (re)configuration of multiple network slices on the same infrastructure that can be independently managed. This provides the impetus for new business models and third party operators, that …
-
Deep reinforcement learning control of a 2D soft robotic arm
This thesis provides a deep reinforcement learning (DRL) based approach for the development of a control policy for a 2D soft robotic arm. The simulation is based on the SOFA framework, which is a real-time multi-physics simulation package capable of creating models and computing forces for …
-
Data-Driven Physical-Layer Optimization for RF and Optical Communications: Transmitarray Metasurfaces, Contextual-Bandit MUD, and Coherent Optical Links
… infeasible, so a one-dimensional convolutional network with cross-attention is trained to predict the scattering parameters from the binary pixel layout and frequency. Locality is preserved through Hilbert ordering, and passivity, causality, and amplitude smoothness are enforced through …
-
Performance Analysis and Learning Algorithms in Advanced Wireless Networks
… for addressing such demand include extreme network densification with more small-cells, the utilization of high frequency bands, such as the millimeter wave (mmWave) bands and terahertz (THz) bands, where more bandwidth is available, and unmanned aerial vehicle (UAV)-enabled cellular …
Page 1 of 2