Sökning: "policy gradient"

Visar resultat 1 - 5 av 12 uppsatser innehållade orden policy gradient.

  1. 1. Generalizing Deep Deterministic Policy Gradient

    Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS); KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Gustaf Jacobzon; Martin Larsson; [2018]
    Nyckelord :;

    Sammanfattning : We extend Deep Deterministic Policy Gradient, a state of the art algorithm for continuous control, in order to achieve a high generalization capability. To achieve better generalization capabilities for the agent we introduce drop-out to the algorithm one of the most successful regularization techniques for generalization in machine learning. LÄS MER

  2. 2. Real-time System Control with Deep Reinforcement Learning

    Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI); KTH/Skolan för teknikvetenskap (SCI)

    Författare :Gustav Gybäck; Fredrik Röstlund; [2018]
    Nyckelord :;

    Sammanfattning : We reproduce the Deep Deterministic Policy Gradient algorithm presented in the paper Continuous Control With Deep Reinforcement Learning to verify its results. We also strive to explain the necessary machine learning framework needed to understand the algorithm. LÄS MER

  3. 3. Deep reinforcement learning i distribuerad optimering

    Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI); KTH/Skolan för teknikvetenskap (SCI)

    Författare :Marcus Lindström; Jahangir Jazayeri; [2018]
    Nyckelord :;

    Sammanfattning : Reinforcement learning has recently become a promising area of machine learning with significant achievements in the subject. Recent successes include surpassing human experts on Atari games and also AlphaGo becoming the first computer ranked on the highest professional level in the game Go, to mention a few. LÄS MER

  4. 4. Deep Reinforcement Learning for Cavity Filter Tuning

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för beräkningsvetenskap

    Författare :Hannes Larsson; [2018]
    Nyckelord :Reinforcement Learning; Cavity Filter; Deep Learning; Machine Learning; Automation;

    Sammanfattning : In this Master's thesis the option of using deep reinforcement learning for cavity filter tuning has been explored. Several reinforcement learning algorithms have been explained and discussed, and then the deep deterministic policy gradient algorithm has been used to solve a simulated filter tuning problem. LÄS MER

  5. 5. Training Neural Models for Abstractive Text Summarization

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Wojciech Kryściński; [2018]
    Nyckelord :machine learning; deep learning; text summarization; natural language processing; neural networks; recurrent neural networks; reinforcement learning; generative adversarial networks; gans; abstractive text summarization; nlp;

    Sammanfattning : Abstractive text summarization aims to condense long textual documents into a short, human-readable form while preserving the most important information from the source document. A common approach to training summarization models is by using maximum likelihood estimation with the teacher forcing strategy. LÄS MER