Sökning: "Atari"

Visar resultat 1 - 5 av 24 uppsatser innehållade ordet Atari.

  1. 1. Evaluation and Redesign of a Web Interface using Usability Heuristic Principles

    Kandidat-uppsats, Blekinge Tekniska Högskola/Institutionen för datavetenskap

    Författare :Sri Harsha Namburu; Venkata Vamsi Krishna Teeparthi; [2023]
    Nyckelord :Heuristic evaluation; HCI design principles; Redesign; Survey evaluation.;

    Sammanfattning : The main aim of this thesis project is to select and redesign a website which was originally designed without using the HCI design principles. The website “Atari best electronics” (https://www.best-electronics-ca.com/) was chosen and evaluated using usability heuristics. LÄS MER

  3. 2. Improving sample-efficiency of model-free reinforcement learning algorithms on image inputs with representation learning

    Master-uppsats, Göteborgs universitet/Institutionen för data- och informationsteknik

    Författare :Marko Guberina; Betelhem Dejene Desta; [2022-10-14]
    Nyckelord :sample-efficient reinforcement learning; state representation learning; unsupervised learning; autoencoder;

    Sammanfattning : Reinforcement learning struggles to solve control tasks on directly on images. Performance on identical tasks with access to the underlying states is much better. LÄS MER

  4. 3. Explainable Reinforcement Learning for Gameplay

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

    Författare :Àlex Costa Sánchez; [2022]
    Nyckelord :Explainable Artificial Intelligence; Local Interpretable Model-agnostic Explanations; Reinforcement Learning; Shapley Additive Explanations; Intel·ligencia Artificial Interpretable; Explicacions model-agnòstiques localment interpretables; Aprenentatge per reforç; Explicacions additives de Shapley; Förklarbar artificiell intelligent; Lokala tolkningsbara modellagnostiska förklaringar; Förstärkningsinlärning; Shapleys additiv förklaringar;

    Sammanfattning : State-of-the-art Machine Learning (ML) algorithms show impressive results for a myriad of applications. However, they operate as a sort of a black box: the decisions taken are not human-understandable. LÄS MER

  5. 4. Playing Atari Breakout Using Deep Reinforcement Learning

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

    Författare :Jonas Nils Martin Lidman; Simon Jonsson; [2022]
    Nyckelord :Reinforcement learning; CartPole; Breakout; DQN;

    Sammanfattning : This report investigates the implementation of a Deep Reinforcement Learning (DRL) algorithm for complex tasks. The complex task chosen was the classic game Breakout, first introduced on the Atari 2600 console.The selected DRL algorithm was Deep Q-Network(DQN) since it is one of the first and most fundamental DRL algorithms. LÄS MER

  7. 5. The Impact of motion-sensing exercise games on young adults : Take “Ring Fit Adventure” as example

    Magister-uppsats, Högskolan i Skövde/Institutionen för informationsteknologi

    Författare :Jiaxin Li; [2022]
    Nyckelord :exercise game; Ring Fit Adventure; Nintendo switch; fitness; motion-sensing;

    Sammanfattning : With the continued expansion of the market share of video games and the growing numberof obese people in recent years, public and business interests in exercise games have been aroused. The period when exercise games emerged maybe can be counted down from AtariPuffer. LÄS MER