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 46 for “"Fast adaptation"”.

  1. Fast adaptation via meta reinforcement learning

    … in the real world. We develop agents capable of Fast Adaptation, i.e., agents that can learn new tasks efficiently.</p> <p>To this end, we use Meta Reinforcement Learning (Meta-RL), where we teach agents not only to act autonomously, but to learn autonomously. We propose four novel Meta-RL …

    oxford Repository record for Fast adaptation via meta reinforcement learning (opens in a new tab)

  2. Fast adaptation of legacy code for server hosting

    … browsers or thin-client applications. While such adaptation cannot take full advantage of the latest computing and networking technologies, it is critical for the industries to make a smooth and fast transition from the traditional in-house computing to Internet-based computing. We study the …

    concordia Download PDF for Fast adaptation of legacy code for server hosting (opens in a new tab)

  3. Learning in dynamical systems with guarantees: from system identification to safety verification and fast adaptation

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-20 without embargo terms

    uiuc Repository record for Learning in dynamical systems with guarantees: from system identification to safety verification and fast adaptation (opens in a new tab)

  4. A Computational Study on the Structure, Dynamics and Mechanoelectric Transduction of Vestibular Hair cell

    … features, I added channel kinetics such as the fast adaptation. In my study, the Ca²⁺ diffusion kinetics plays a key role in the hair cell adaptations. The Ca²⁺ association rate to the fast adaptation modulator is postulated to govern the fast adaptation. I assumed that two factors--the tip link …

    vt Repository record for A Computational Study on the Structure, Dynamics and Mechanoelectric Transduction of Vestibular Hair cell (opens in a new tab)

  5. LEARNING ROBOT CONTROL VIA BILEVEL OPTIMIZATION

    … accurate disturbance estimation and rapid adaptation. The second contribution presents a trust-region policy optimization method that further enhances NeuroMHE training, reducing neural network size and data while maintaining accuracy. The third contribution develops Auto-Multilift, a …

    nus Repository record for LEARNING ROBOT CONTROL VIA BILEVEL OPTIMIZATION (opens in a new tab) Download file for LEARNING ROBOT CONTROL VIA BILEVEL OPTIMIZATION (opens in a new tab)

  6. The Integration of Information Relevant to a Manual Control Task

    … be processed most efficiently and result in fast adaptation and (2) detection with the proximal hand would be more efficient.

    uiuc Repository record for The Integration of Information Relevant to a Manual Control Task (opens in a new tab)

  7. Robust adaptive control of induction machines using the L1 control scheme

    … that robustness may be maintained even with very fast adaptation. This controller is limited by the flux observer used to provide information about flux magnitude and direction.

    uiuc Repository record for Robust adaptive control of induction machines using the L1 control scheme (opens in a new tab)

  8. LEARNING GENERALIZABLE REPRESENTATIONS IN REINFORCEMENT LEARNING

    … on two aspects of good generalization ability: fast adaptation and zero-shot transfer. We first study the task-agnostic Laplacian representations and introduce a new generalized graph drawing objective, which greatly improves the quality of the learned Laplacian representations. Second, we …

    nus Repository record for LEARNING GENERALIZABLE REPRESENTATIONS IN REINFORCEMENT LEARNING (opens in a new tab) Download file for LEARNING GENERALIZABLE REPRESENTATIONS IN REINFORCEMENT LEARNING (opens in a new tab)

  9. Prediction-Guided Performance-Energy Trade-Off With Continuous Run-Time Adaptation

    … decomposition and explicit change detection for fast adaptation. In addition to the DVFS control, I show that the proposed prediction model can be used to intelligently select a core in a heterogeneous system. Experimental results on the ARM big.LITTLE platform show that the DVFS controller and …

    cornell Repository record for Prediction-Guided Performance-Energy Trade-Off With Continuous Run-Time Adaptation (opens in a new tab)

  10. Hierarchical reinforcement learning for adaptive and autonomous decision-making in robotics

    … implement two techniques to enable this adaptation. First, we implement a hierarchical Reinforcement Learning architecture that uses differentiated sub-policies governed by a hierarchical controller to enable fast adaptation. Second we introduce a confidence-based training process for the …

    uiuc Repository record for Hierarchical reinforcement learning for adaptive and autonomous decision-making in robotics (opens in a new tab)

  11. Light Stimulation of Sensory Hair Cells

    … this study was to elucidate the role of Ca2+ in fast adaptation, a process thought to underlie a hair bundle's ability to amplify stimuli. I aimed to do this by generating intracellular surges in Ca2+ concentration without altering the state of the mechanotransduction channel or its associated …

    rockefeller Repository record for Light Stimulation of Sensory Hair Cells (opens in a new tab)

  12. Scene adaptive crowd counting

    … of a crowd counting model in a way to facilitate fast adaptation to the target scene. Second, we introduce a new problem called unlabeled scene adaptive crowd counting. More specifically, we propose to use few unlabeled images from the target scene to perform the adaptation. We introduce a novel …

    manitoba Repository record for Scene adaptive crowd counting (opens in a new tab)

  13. Broad Generalization through Domain Transfer: Abstractions and Algorithms

    … robust, capable of broad generalization, and fast adaptation? In this thesis, we outline the importance of domain transfer as a key component to achieve the aforementioned capabilities. Domain transfer refers to the ability of an AI agent to draw upon experiences from related tasks and …

    washington Repository record for Broad Generalization through Domain Transfer: Abstractions and Algorithms (opens in a new tab)

  14. Lexical syntax for statistical machine translation

    … scalability, computational efficiency and fast adaptation to new languages and domains. However, current approaches of Phrase-based SMT lacks the capabilities of producing more grammatical translations and handling long-range reordering while maintaining the grammatical structure of the …

    dcu Download PDF for Lexical syntax for statistical machine translation (opens in a new tab)

  15. Better Generalization with Less Human Annotation Using Meta-Learning and Self-Supervised Learning for Image Analysis

    … also called “learning to learn”, which acquires fast adaptation capability over a collection of related tasks and uses it to improve its future learning performance. Self-supervised learning, on the other hand, tries to leverage all useful information from the unlabeled training data itself. It …

    houston Repository record for Better Generalization with Less Human Annotation Using Meta-Learning and Self-Supervised Learning for Image Analysis (opens in a new tab)

  16. Deep reinforcement learning agents for industrial control system design

    … wherein a generalized agent is trained for the fast adaptation across a broad collection of dynamics. A key design element is the ability to leverage model-based information offline during training while maintaining a model-free policy structure for interacting with novel processes. Beyond PI …

    ubc Repository record for Deep reinforcement learning agents for industrial control system design (opens in a new tab) Download PDF for Deep reinforcement learning agents for industrial control system design (opens in a new tab)

  17. ONLINE CONTROLLER ADAPTATION WITH META-LEARNED MODELS

    … environment or on every task, necessitating adaptation to different operating conditions. However, existing methods fall short in some key ways. Classical methods for controller adaptation and tuning are restrictive in their assumptions, while modern data-driven methods struggle with sample …

    penn Repository record for ONLINE CONTROLLER ADAPTATION WITH META-LEARNED MODELS (opens in a new tab)

  18. Experimental Analysis of Skull Remodeling and Change in Intracranial Volume with a soft Orthosis in Canine Models

    … All 14 beagles with a soft orthosis showed very fast adaptation of the head to the orthosis just 2 weeks into the experiment, and they continued to develop a long and narrow head shape throughout the 7-week experimental period. At 7 weeks, they showed significantly shorter width and longer head …

    ajou Repository record for Experimental Analysis of Skull Remodeling and Change in Intracranial Volume with a soft Orthosis in Canine Models (opens in a new tab) Embargoed until 9999-12-31

  19. Role of hippocampal network activities in stress- and fear-related processes

    … agents is an acute process, permitting fast adaptation to new attention-requiring situations in vivo.

    fu-berlin Repository record for Role of hippocampal network activities in stress- and fear-related processes (opens in a new tab)

  20. Έλεγχος συνεργατικών ρομπότ για ασφαλή λειτουργία και υποβοηθούμενη κιναισθητική καθοδήγηση με χρήση δυναμικών συστημάτων και επιβολή περιορισμών

    … progressive automation of a task, and c) the fast adaptation of kinematic behaviors which encode harmonic oscillations to the forces exerted by the user. The proposed control laws of the thesis are experimentally validated and compared with state-of-the-art methods, utilizing the KUKA LWR4+ …

    greece Repository record for Έλεγχος συνεργατικών ρομπότ για ασφαλή λειτουργία και υποβοηθούμενη κιναισθητική καθοδήγηση με χρήση δυναμικών συστημάτων και επιβολή περιορισμών (opens in a new tab)

Page 1 of 3