Sökning: "information rewards"

Visar resultat 1 - 5 av 72 uppsatser innehållade orden information rewards.

  1. 1. Reinforcement Learning– Intelligent Weighting of Monte Carlo and Temporal Differences

    Uppsats för yrkesexamina på avancerad nivå, Lunds universitet/Institutionen för reglerteknik

    Författare :Martin Christiansson; [2019]
    Nyckelord :Technology and Engineering;

    Sammanfattning : In Reinforcement learning the updating of the value functions determines the information spreading across the state/state-action space which condenses the valuebased control policy. It is important to have an information propagation across the value domain in a manner that is effective. LÄS MER

  2. 2. Showrooming – Displayed and played. : - A case study from a brick-and-mortar perspective

    Master-uppsats, Uppsala universitet/Företagsekonomiska institutionen; Uppsala universitet/Företagsekonomiska institutionen

    Författare :Johanna Westerlund; Mikael Westin; [2018]
    Nyckelord :Showrooming; Omni- and Multichannel retailing; Freeriding; Research Shopping;

    Sammanfattning : Purpose - The purpose of this study was to deepen the understanding of how showrooming affect the exploited brick-and-mortar businesses. This was done by investigating an industry characterized by high levels of employee knowledge where the expertise of the personnel create showrooming incentives. LÄS MER

  3. 3. Hedging Your Bets: The Prospects of Cryptocurrency Use in Online Gambling : A Mixed-Methods Study

    Master-uppsats, Umeå universitet/Företagsekonomi; Umeå universitet/Företagsekonomi

    Författare :Nicolas Werle; Liina Lehtonen; [2018]
    Nyckelord :cryptocurrency; online gambling; diffusion of innovation; disruptive technology; blockchain; consumer behaviour;

    Sammanfattning : Since its initial inception, cryptocurrency has hit the world with both intrigue and skepticism. It was acting as an alternative form of currency that people could use that required no regulative authority to back it. LÄS MER

  4. 4. 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

  5. 5. The key role of dopamine as the neural correlate of intrinsic motivation and trait plasticity

    Kandidat-uppsats, Högskolan i Skövde/Institutionen för biovetenskap

    Författare :Lars Temnerud; [2018]
    Nyckelord :dopamine; intrinsic motivation; metatrait plasticity; personality neuroscience; the five factor model; exploration;

    Sammanfattning : Self-determination theory (SDT), a motivation theory, consists of motivation types: intrinsic motivation, extrinsic motivation, and amotivation, where the social environment is important. SDT’s motivation orientations are about individual differences in people’s tendencies to orient towards environments. LÄS MER