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 132 for “"Continuous Control"”.

  1. Probabilistic machine learning: methods and applications to continuous control

    … and variational techniques to the field a continuous control. Firstly, we describe how reinforcement learning can be viewed as probabilistic inference and introduce a novel algorithm for learning priors in reinforcement learning leading to substantial improvement in learning speed and final …

    oxford Repository record for Probabilistic machine learning: methods and applications to continuous control (opens in a new tab)

  2. Efficient Constrained Continuous Control-Set Predictive Control of Three-Phase Inverters

    Model Predictive Control (MPC) is a promising approach for constrained power electronic systems due to its simple formulation and its capability to handle system constraints systematically. However, two major challenges hinder the practical implementation of MPC in power electronics: (i) the strong …

    houston Repository record for Efficient Constrained Continuous Control-Set Predictive Control of Three-Phase Inverters (opens in a new tab) Embargoed until 2028-05-01

  3. Online Active Preference Learning from Sparse Expert Feedback in Continuous Control

    In continuous-control reinforcement learning, direct reward design can bedifficult when desired behavior is multi-dimensional, and expert feedback is often too limited to query exhaustively. This thesis develops an online active-preference learning framework that combines a fixed expert log-density …

    oregon Repository record for Online Active Preference Learning from Sparse Expert Feedback in Continuous Control (opens in a new tab)

  4. Reinforcement Learning Methods in Continuous Control: Analyzing Strategies for Goal Selection and Experience Replay for Different Robotic Tasks

    Surgical robots require highly precise control mechanisms to assist doctors during complex and prolonged procedures. Similar to the human brain, robots in surgical environments must be sample-efficient and capable of learning from limited real-world experiences. Reinforcement Learning (RL) provides …

    concordia Download PDF for Reinforcement Learning Methods in Continuous Control: Analyzing Strategies for Goal Selection and Experience Replay for Different Robotic Tasks (opens in a new tab)

  5. Sample-Efficient Methods for Real-World Deep Reinforcement Learning

    … different problem settings: multi-agent discrete control, continuous control, and continuous control from image observations. For multi-agent discrete control, the thesis proposes a sample-efficient model-based approach that plans using known dynamics models, to learn to play imperfect-information …

    aalto Repository record for Sample-Efficient Methods for Real-World Deep Reinforcement Learning (opens in a new tab)

  6. Musical Gesture through the Human Computer Interface: An Investigation using Information Theory

    … investigate human ability to communicate using continuous control sensors with a particular focus on informing the design of digital musical instruments. There is an active practice of building and evaluating such instruments, for instance, in the New Interfaces for Musical Expression (NIME) …

    lsu-thes Repository record for Musical Gesture through the Human Computer Interface: An Investigation using Information Theory (opens in a new tab)

  7. Learning Trajectories from Human Demonstration via Time Invariant Dynamical Systems

    … objective for each demonstrated task, optimal control methods cannot be directly applied. Two primary paradigms have emerged to overcome the limitation: 1) inverse learning and 2) imitation learning. In this dissertation, I formulate several time-invariant and stable dynamic system-based LfD …

    unh-thes Repository record for Learning Trajectories from Human Demonstration via Time Invariant Dynamical Systems (opens in a new tab)

  8. Generalizable Learning for Natural Language Instruction Following on Physical Robots

    … robots by mapping raw visual observations to continuous control. The approach reconsiders the full robotics stack, including solving perception, planning, mapping, and control challenges, all with a focus on enabling behavior specification in natural language. The presented approach achieved …

    cornell Repository record for Generalizable Learning for Natural Language Instruction Following on Physical Robots (opens in a new tab)

  9. Energy-Efficient Computing for Scalable and Sustainable AI

    … real-world application scenarios such as complex continuous control tasks, SNNs often lack the performance optimizations of traditional artificial neural networks. To address this issue, researchers have combined SNNs with Deep Reinforcement Learning (DeepRL) algorithms to utilize their …

    ut-knoxville Repository record for Energy-Efficient Computing for Scalable and Sustainable AI (opens in a new tab)

  10. Stabilization of a space vehicle antenna mount

    … in detail. The system is implemented by both a continuous control and a digital control.</p><p>1ii</p>

    ut-knoxville Repository record for Stabilization of a space vehicle antenna mount (opens in a new tab)

  11. Design and Parametric Study of a MEMS-based Reservoir Computer for Reinforcement Learning

    … reservoir computer to solve both discrete and continuous control tasks. MEMS-based reservoirs are low-power, compact, and their natural frequencies (kHz to MHz) pair well with real-time control loops. To explore the relationship between reservoir dynamics and learning performance, a parametric …

    calpoly Repository record for Design and Parametric Study of a MEMS-based Reservoir Computer for Reinforcement Learning (opens in a new tab)

  12. Artificial Neural Network-Based Robotic Control

    … The applications of ANNs range from process control to pattern recognition and, with increasing importance, robotics. This paper demonstrates continuous control of a robot using the deep deterministic policy gradients (DDPG) algorithm, an actor-critic reinforcement learning strategy, …

    calpoly Repository record for Artificial Neural Network-Based Robotic Control (opens in a new tab)

  13. Um desacoplamento canônico para sistemas lineares multivariáveis

    … decoupling of the system. System controllability and observability are studied in this framework. Although the decoupling scheme is developed for continuous control systems, it is also valid for discrete-time linear systems. A Fortran computer program is presented which calculates …

    brazil-uerj Repository record for Um desacoplamento canônico para sistemas lineares multivariáveis (opens in a new tab)

  14. Satellite relative motion propagation and control in the presence of J2 perturbations

    … using impulsive thrust (velocity increments) or continuous control. This thesis presents a method to obtain the optimal velocity increments through numerical optimization, utilizing the analytical technique developed for relative orbit propagation. A continuous control law is also developed using …

    tamu Repository record for Satellite relative motion propagation and control in the presence of J2 perturbations (opens in a new tab)

  15. Sliding control design and implementation on a single-link flexible arm

    The sliding model control is known as a robust control that is able to work under the uncertainties of modeling error and the environmental disturbances. The objective of this research is to design the simple control (sliding control) algorithms for a single-link flexible arm and to study the …

    nps Repository record for Sliding control design and implementation on a single-link flexible arm (opens in a new tab)

  16. Dynamic reconfiguration of shipboard power systems preserving stability

    … systems. With discrete (relays and breakers) and continuous states (voltages and angles) and controls (field currents and timers) a reconfigurable power system provides a most appropriate example to be analyzed under the theory of hybrid systems. We consider shipboard power systems as an example …

    texas Repository record for Dynamic reconfiguration of shipboard power systems preserving stability (opens in a new tab) Restricted access

  17. The Analysis and Design of Continuous Pressure Control System

    <p> The continuous control of hydraulic pressure as a predetermined function of an independent variable is considered for the cases of low, intermediate and high pressure levels. A simple control system for the continuous regulation of low pressure is briefly discussed, and a means of extending its …

    mcmaster Repository record for The Analysis and Design of Continuous Pressure Control System (opens in a new tab)

  18. An extended process automation system : an approach based on a multi-agent system

    … process automation systems at higher levels of control. Anticipated benefits of the specification include enhanced reconfigurability, responsiveness and flexibility properties of process automation. Previous research concerning applications of MAS in process automation has been more limited than …

    aalto Repository record for An extended process automation system : an approach based on a multi-agent system (opens in a new tab)

Page 1 of 7