Sökning: "Förstärkningsinlärning"

Visar resultat 1 - 5 av 95 uppsatser innehållade ordet Förstärkningsinlärning.

  1. 1. LEO Satellite Connectivity for flying vehicles

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

    Författare :Jinxuan Chen; [2023]
    Nyckelord :LEO satellite network; satellite connectivity strategy; Nash-SAC; flying vehicles; LEO:s satellitnät; Strategi för satellitanslutning; Nash-SAC; flygande fordon;

    Sammanfattning : Compared with the terrestrial network (TN), which can only support limited covered areas, satellite communication (SC) can provide global coverage and high survivability in case of an emergency like an earthquake. Especially low-earth orbit (LEO) satellites, as a promising technology, which is integral to achieving the goal of global seamless coverage and reliable communication, catering to 6G’s communication requirements. LÄS MER

  3. 2. Decreasing Training Time of Reinforcement Learning Agents for Remote Tilt Optimization using a Surrogate Neural Network Approximator

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

    Författare :Jiaming Huang; [2023]
    Nyckelord :;

    Sammanfattning : One possible application of reinforcement learning in the telecommunication field is antenna tilt optimization. However, one of key challenges we face is that the use of handcrafted simulators as environments to provide information for agents is often time-consuming regarding training reinforcement learning agents. LÄS MER

  4. 3. Explainable AI for Multi-Agent Control Problem

    Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknik

    Författare :Hanna Prokopova; [2023]
    Nyckelord :;

    Sammanfattning : This report presents research on the application of policy explanation techniques in the context of coordinated reinforcement learning (CRL) for mobile network optimization. The goal was to improve the interpretability and comprehensibility of decision-making processes in multi-agent environments, with a particular focus on the Remote Antenna Tilt (RET) problem. LÄS MER

  5. 4. S-MARL: An Algorithm for Single-To-Multi-Agent Reinforcement Learning : Case Study: Formula 1 Race Strategies

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

    Författare :Marinaro Davide; [2023]
    Nyckelord :Reinforcement Learning; Single-to-Multi-Agent; Learning Stability; Exploration-Exploitation trade-off; Race Strategy Optimization; Förstärkningsinlärning; Från en till flera agenter; Stabilitet vid inlärning; Utforskning-exploatering; Optimering av tävlingsstrategier;

    Sammanfattning : A Multi-Agent System is a group of autonomous, intelligent, interacting agents sharing an environment that they observe through sensors, and upon which they act with actuators. The behaviors of these agents can be either defined upfront by programmers or learned by trial-and-error resorting to Reinforcement Learning. LÄS MER

  7. 5. Smart Tracking for Edge-assisted Object Detection : Deep Reinforcement Learning for Multi-objective Optimization of Tracking-based Detection Process

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

    Författare :Shihang Zhou; [2023]
    Nyckelord :Tracking-By-Detection; Deep Reinforcement Learning; Multi-Objective Optimization; Spårning genom detektion; Djup förstärkningsinlärning; Multiobjektiv optimering;

    Sammanfattning : Detecting generic objects is one important sensing task for applications that need to understand the environment, for example eXtended Reality (XR), drone navigation etc. However, Object Detection algorithms are particularly computationally heavy for real-time video analysis on resource-constrained mobile devices. LÄS MER