Sökning: "reinforcement learning"

Visar resultat 21 - 25 av 457 uppsatser innehållade orden reinforcement learning.

  1. 21. PVCFA: Principal Variation Context Feature Attribution : Distributed Chess for Perturbation-based Saliency Maps

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

    Författare :Marco Molinari; [2023]
    Nyckelord :Chess; Perturbation; Saliency maps; Multiagent; Reinforcement Learning; Schack; Perturbation; Saliency maps; Multiagent; Reinforcement Learning;

    Sammanfattning : The research and development field of computer chess improved more in the last 5 years than in the whole history of computers. Unfortunately these unprecedented results comes with techniques that don’t leave much space to intuition and comprehensibility for humans. LÄS MER

  3. 22. A hierarchical neural network approach to learning sensor planning and control

    Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Datorteknik

    Författare :Nicke Löfwenberg; [2023]
    Nyckelord :sensor planning; hierarchical reinforcement learning; reinforcement learning; sensor control; camera control; sensorplanering; hierarkisk förstärkningsinlärning; förstärkningsinlärning; sensorkontroll; kamerakontroll;

    Sammanfattning : The ability to search their environment is one of the most fundamental skills for any living creature. Visual search in particular is abundantly common for almost all animals. LÄS MER

  4. 23. Safe Reinforcement Learning for Social Human-Robot Interaction : Shielding for Appropriate Backchanneling Behavior

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

    Författare :Mohamed Akif; [2023]
    Nyckelord :Human-Robot Interaction; Backchanneling; Social Robots; Safe Reinforcement Learning; Shielding; Recurrent Neural Network; Gated Recurrent Unit; Människa-Robot Interaktion; Uppbackning; Sociala Robotar; Säker Förstärkningsinlärning; Avskärmning; Återkommande Neurala Nätverk; Gated Återkommande Enhet;

    Sammanfattning : Achieving appropriate and natural backchanneling behavior in social robots remains a challenge in Human-Robot Interaction (HRI). This thesis addresses this issue by utilizing methods from Safe Reinforcement Learning in particular shielding to improve social robot backchanneling behavior. LÄS MER

  5. 24. Optimal Gait Control of Soft Quadruped Robot by Model-based Reinforcement Learning

    Master-uppsats, KTH/Skolan för industriell teknik och management (ITM)

    Författare :Niu Xuezhi; [2023]
    Nyckelord :Quadruped Robots; Soft Robotics; Reinforcement Learning; Gait Control; Model-Based Control Optimization; Kvadrupedroboter; Mjukrobotik; Förstärkningsinlärning; Gångkontroll; Optimering av robotkontroll;

    Sammanfattning : Quadruped robots offer distinct advantages in navigating challenging terrains due to their flexible and shock-absorbing characteristics. This flexibility allows them to adapt to uneven surfaces, enhancing their maneuverability. LÄS MER

  7. 25. Enhancing video game experience with playtime training and tailoring of virtual opponents : Using Deep Q-Network based Reinforcement Learning on a Multi-Agent Environment

    Master-uppsats,

    Författare :Nishant Pillai; Roberto Giaconia; [2023]
    Nyckelord :;

    Sammanfattning : When interacting with fictional environments, the users' sense of immersion can be broken when characters act in mechanical and predictable ways. The vast majority of AIs for such fictional characters, that control their actions, are statically scripted, and expert players can learn strategies that take advantage of this to easily win challenges that were intended to be hard. LÄS MER