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 50 for “"Deep reinforcement learning (DRL)"”.

  1. Model-free tracking control of an optical fiber drawing process using deep reinforcement learning

    A deep reinforcement learning (DRL) approach for tracking control of an optical fiber drawing process is developed and evaluated. The DRL-based control is capable of regulating the fiber diameter to track either steady or varying reference trajectories in the presence of stochasticity and …

    mit Repository record for Model-free tracking control of an optical fiber drawing process using deep reinforcement learning (opens in a new tab)

  2. Encoding the Sensor Allocation Problem for Reinforcement Learning

    … are allocated to observe resident space objects. Deep reinforcement learning (DRL) techniques, with their ability to be trained on simulated environments, which are readily available for the SSA sensor allocation problem, and demonstrated performance in other fields, have potential to exceed …

    vt Repository record for Encoding the Sensor Allocation Problem for Reinforcement Learning (opens in a new tab)

  3. Towards Optimal Grasping Of Unknown Objects Using Deep Reinforcement Learning

    … objects, can be approached empirically. Deep reinforcement learning (DRL) is an empirical method that does not require a dataset and learns tasks by interacting with an environment. This study aims to utilize DRL algorithms to perform grasping by creating a novel grasping environment for …

    york Repository record for Towards Optimal Grasping Of Unknown Objects Using Deep Reinforcement Learning (opens in a new tab)

  4. DEEP REINFORCEMENT LEARNING FOR ROBOT-ASSISTED SURGICAL TRAINING

    … of trainee surgeons is extended. To shorten the learning curve of hand-eye coordination in the laparoscopic surgery, guidance from a Deep Reinforcement Learning (DRL) intelligent agent is proposed to support the trainee in the surgical training. In this thesis, a Cyber-Physical System (CPS) is …

    nus Repository record for DEEP REINFORCEMENT LEARNING FOR ROBOT-ASSISTED SURGICAL TRAINING (opens in a new tab)

  5. 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 …

    uiuc Repository record for Deep reinforcement learning control of a 2D soft robotic arm (opens in a new tab)

  6. From Static to Adaptive: Dynamic Cost Function Weight Adaptation in Hierarchical Reinforcement Learning for Sustainable 6G Radio Access Networks

    … and Quality of Service (QoS) degradation in Deep Reinforcement Learning (DRL)-based BS switching. Using a realistic spatio-temporal dataset, we show that static cost weights lead to suboptimal performance under varying traffic conditions. To address this, we propose a Hierarchical …

    vt Repository record for From Static to Adaptive: Dynamic Cost Function Weight Adaptation in Hierarchical Reinforcement Learning for Sustainable 6G Radio Access Networks (opens in a new tab)

  7. Data-Driven Voltage Control of DERs Integrated Distribution Grids Using Deep Reinforcement Learning

    … the voltage of the distribution network, machine Learning (ML) based VVC/VVO approaches especially deep reinforcement learning (DRL) based VVC approaches has become popular for real time control of the voltage. DRL can optimally control the reactive power set-point of the inverter to minimize the …

    unr Repository record for Data-Driven Voltage Control of DERs Integrated Distribution Grids Using Deep Reinforcement Learning (opens in a new tab)

  8. Playing Tetris with deep reinforcement learning

    … cleared in an average game. In recent years, deep reinforcement learning (DRL) has achieved outstanding performance with Atari and Go games. An initial attempt by Stevens and Pradhan (2016) to use deep reinforcement learning to play Tetris was unsuccessful. The objective of this thesis is to …

    uiuc Repository record for Playing Tetris with deep reinforcement learning (opens in a new tab)

  9. Model-based approaches for learning control from multi-modal data

    Methods like deep reinforcement learning (DRL) have gained increasing attention when solving very general continuous control tasks in a model-free end-to-end fashion. However, there has been great difficulty in applying these algorithms to real-world systems due to poor sample efficiency and …

    uiuc Repository record for Model-based approaches for learning control from multi-modal data (opens in a new tab)

  10. ACADIA: Efficient and Robust Adversarial Attacks Against Deep Reinforcement Learning

    Existing adversarial algorithms for Deep Reinforcement Learning (DRL) have largely focused on identifying an optimal time to attack a DRL agent. However, little work has been explored in injecting efficient adversarial perturbations in DRL environments. We propose a suite of novel DRL adversarial …

    vt Repository record for ACADIA: Efficient and Robust Adversarial Attacks Against Deep Reinforcement Learning (opens in a new tab)

  11. Joint Vehicle Dispatching and Redeployment for Emergency Medical Services with Multi-Critic Reinforcement Learning

    … problem) or as two separate systems to optimize. Deep Reinforcement Learning (DRL) has been growing in popularity over the past half decade, and applications of these advances are still underutilized for this problem. While methods within the DRL family have been applied to this problem, they …

    fsu-retro

  12. Realtime Vehicle Route Optimisation via DQN for Sustainable and Resilient Urban Transportation Network

    … a real time manner. In this thesis, we propose a deep reinforcement learning (DRL) method to build a real-time intelligent vehicle navigation system for sustainable and resilient urban transportation network. We designed two rewards methods travel time based and vehicle emissions impact (VEI) …

    liverpool-jm Repository record for Realtime Vehicle Route Optimisation via DQN for Sustainable and Resilient Urban Transportation Network (opens in a new tab)

  13. Enhancing Engineering Education: Integration of the Desktop Fiber Extrusion Device (FrED) for Hands-On Learning in Smart Manufacturing.

    … FrED models, designed to provide hands-on learning experiences remotely, which is increasingly pertinent in the evolving landscape of engineering education. Through iterative design and implementation of control systems, including Proportional-Integral-Derivative (PID) and Deep

    mit Repository record for Enhancing Engineering Education: Integration of the Desktop Fiber Extrusion Device (FrED) for Hands-On Learning in Smart Manufacturing. (opens in a new tab)

  14. Digital Twin Platform for Drone Applications

    … in dynamics, control, computer vision, and deep learning. Despite their importance, existing simulators face limitations in modularity, scalability, and multidisciplinary integration, while the persistent sim-to-real gap remains a major challenge. Nevertheless, simulators are indispensable, …

    york Repository record for Digital Twin Platform for Drone Applications (opens in a new tab)

  15. Learning to Plan by Learning Rules

    … to relearn everything from scratch. By contrast, deep reinforcement learning (DRL) algorithms are ill-suited to learning policies in rule-based environments, as satisfying rules often involves executing lengthy tasks with sparse rewards. Furthermore, learned DRL policies are difficult if not …

    mit Repository record for Learning to Plan by Learning Rules (opens in a new tab)

  16. Generative Chatbot Framework for Cybergrooming Prevention

    … in the context of cybergrooming, we take deep reinforcement learning (DRL)-based dialogue generation to simulate the authentic conversations between a perpetrator and a potential victim. The design and development of the SERI are motivated to provide a safe and authentic chatting …

    vt Repository record for Generative Chatbot Framework for Cybergrooming Prevention (opens in a new tab)

  17. Advanced Energy Management Strategies for Multi-Energy Community Microgrids

    … energy management, rule-based control (RBC) and deep reinforcement learning (DRL) techniques were deployed. The DRL-based approach enables adaptive decision making and improves the response of the system to variable load demands, renewable fluctuations, and grid interactions. The proposed energy …

    unsw Repository record for Advanced Energy Management Strategies for Multi-Energy Community Microgrids (opens in a new tab)

  18. An Invisible Issue of Task Underspecification in Deep Reinforcement Learning Evaluations

    Performance evaluations of Deep Reinforcement Learning (DRL) algorithms are an integral part of the scientific progress of the field. However, standard performance evaluation practices in evaluating algorithmic generalization of DRL methods within a task can be unreliable and misleading if not …

    mit Repository record for An Invisible Issue of Task Underspecification in Deep Reinforcement Learning Evaluations (opens in a new tab)

  19. NMR studies of quantum thermalization

    … the Hamiltonian engineering sequences, the deep reinforcement learning (DRL) techniques are adopted. The sequences designed by the DRL show better decoupling performance than the previously best known sequence. Beyond that, a new and advantageous pattern is discovered from the DRL sequences …

    mit Repository record for NMR studies of quantum thermalization (opens in a new tab)

  20. Deep Reinforcement Learning for Multirotor Flight Control: A Comparative Study of Sim-to-Real Training and Real-World Performance

    This dissertation investigates Deep Reinforcement Learning (DRL) for low-level flight control of multirotor unmanned aerial vehicles (UAVs), focusing on factors that most influence sim-to-real policy transfer. Using the Proximal Policy Optimization (PPO) algorithm, extensive ablation studies …

    vt Repository record for Deep Reinforcement Learning for Multirotor Flight Control: A Comparative Study of Sim-to-Real Training and Real-World Performance (opens in a new tab)

Page 1 of 3