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 1732 for “"RL"”.

  1. XML-RL: An XML query system.

    regina Repository record for XML-RL: An XML query system. (opens in a new tab)

  2. INTELLIGENT GEOSYSTEM ENABLED BY REINFORCEMENT LEARNING (RL)

    … slopes enabled by Deep Reinforcement Learning (DRL), a subfield of machine learning for automated decision-making. The purpose is to develop an intelligent geosystem that can minimize operating costs and enhance the system’s safety without introducing human errors and interventions. First, to …

    mtu Repository record for INTELLIGENT GEOSYSTEM ENABLED BY REINFORCEMENT LEARNING (RL) (opens in a new tab)

  3. LEVERAGING RL MULTI-MODELS FOR WARGAMING AI

    … proof-of-concept for the reinforcement learning (RL) multi-model and the hierarchical multi-model, a type of multi-model that leverages the inherent hierarchical structure of military units. Furthermore, this thesis shows how the application of temporal abstraction and an orientation transformer …

    nps Repository record for LEVERAGING RL MULTI-MODELS FOR WARGAMING AI (opens in a new tab)

  4. GRLSR : a goal-conditioned RL related state representation learning method

    In the field of reinforcement learning (RL), representation learning has been proven to be a useful tool in robotic tasks. However, many representation learning methods for RL tasks are developed without explicit objectives linked to RL theory. The efficiency of representation learning for …

    texas Repository record for GRLSR : a goal-conditioned RL related state representation learning method (opens in a new tab)

  5. Application Layer Optimization of Big Data Transfer Throughput Using RL

    … pipelining) using Deep Reinforcement Learning (DRL). We compare our novel solution with other approaches using real-life transfer traces we have collected over time. The experimental results show that our DRL-based approach significantly outperforms other solutions in this area.

    buffalo Repository record for Application Layer Optimization of Big Data Transfer Throughput Using RL (opens in a new tab)

  6. Transfer Function Synthesis Based on Cascaded Rc and Rl Networks

    Made available in DSpace on 2014-12-04T21:03:18Z (GMT). No. of bitstreams: 1 6100095.pdf: 4081980 bytes, checksum: ba36a9468461154c544803ca924a0055 (MD5) Previous issue date: 1960

    uiuc Repository record for Transfer Function Synthesis Based on Cascaded Rc and Rl Networks (opens in a new tab)

  7. Swimming upstream: Pathways of new engineering faculty at non-Rl institutions

    The landscape of engineering academia is varied, yet many graduate students are socialized to aspire to a tenure-track faculty position at a research-intensive institution, and are told that teaching is a necessary activity in order to focus on research. However, some graduate students seek out a …

    purdue-thes Repository record for Swimming upstream: Pathways of new engineering faculty at non-Rl institutions (opens in a new tab)

  8. NeurWIN: Neural Whittle Index Network for Restless Bandits via Deep RL

    Whittle index policy is a powerful tool to obtain asymptotically optimal solutions for the notoriously intractable problem of restless bandits. However, finding the Whittle indices remains a difficult problem for many practical restless bandits with convoluted transition kernels. This thesis …

    tamu Repository record for NeurWIN: Neural Whittle Index Network for Restless Bandits via Deep RL (opens in a new tab)

  9. CORTICO-MUSCLE ENCODING: EVOKING PRINCIPLES OF CORTICO-MUSCLE CONNECTIVITY WITH RL-ICMS

    … long-duration intracortical microstimulation (RL-ICMS) to elicit the organization and function of the rhesus macaque primary motor cortex (M1). The first focus concerns the timing between cortical activity and corresponding muscle activity, of which previous studies have revealed a broad range …

    ku Repository record for CORTICO-MUSCLE ENCODING: EVOKING PRINCIPLES OF CORTICO-MUSCLE CONNECTIVITY WITH RL-ICMS (opens in a new tab)

  10. Error correction for depolarising noise on a quantum system using deep RL

    We implement a quantum error correction algorithm for the depolarized noise model on the topological toric code using deep reinforcement learning. An action-value Q-function encodes the discounted value of applying any of the three pauli operators ( x, y, z) to a specific qubit given the entire set …

    chalmers Repository record for Error correction for depolarising noise on a quantum system using deep RL (opens in a new tab)

  11. When process rewards fail : synthetic negatives and specification gaming in PRM-based RL

    Process-based reinforcement learning (RL) supervises the individual reasoning steps of a language model rather than only its final answer. The same denser signal that promises more faithful reasoning also creates new opportunities for reward hacking: the policy maximises a Process Reward Model …

    texas Repository record for When process rewards fail : synthetic negatives and specification gaming in PRM-based RL (opens in a new tab)

  12. UCB-MAPPO: Uncertainty-Aware Multi-Agent RL for Cooperative Robot Navigation and Coverage

    … exploration, which most multi-agent RL algorithms use, is too undirected for the sparse-reward conditions of real robot navigation and coverage tasks. This thesis presents UCB-MAPPO, which replaces entropy exploration with Upper Confidence Bound bonuses derived from Monte Carlo …

    texas-state Repository record for UCB-MAPPO: Uncertainty-Aware Multi-Agent RL for Cooperative Robot Navigation and Coverage (opens in a new tab)

  13. Modeling alternating current rotating electrical machines using constant-parameter RL-branch interfacing circuits

    … proposes a unified constant-parameter decoupled RL-branch circuit in abc-phase coordinates (with optional zero-sequence). The proposed circuits are based on voltage-behind-reactance (VBR) formulation and can be used for interfacing both induction and synchronous machine models. The new models …

    ubc Repository record for Modeling alternating current rotating electrical machines using constant-parameter RL-branch interfacing circuits (opens in a new tab) Download PDF for Modeling alternating current rotating electrical machines using constant-parameter RL-branch interfacing circuits (opens in a new tab)

  14. The Finite Embeddability Property for Some Noncommutative Knotted Varieties of RL and DRL

    … general case, the free object in the class is fairly complicated, so we identify instead an object outside the class, which is both free and structured enough to allow us to prove the result. In the last section, we extend our result to cover some other subvarieties of knotted residuated lattices. …

    denver Repository record for The Finite Embeddability Property for Some Noncommutative Knotted Varieties of RL and DRL (opens in a new tab)

Page 1 of 87