Sökning: "multi-agent"

Visar resultat 6 - 10 av 205 uppsatser innehållade ordet multi-agent.

  1. 6. 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

  3. 7. 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

  4. 8. On the strategic abilities gained by using knowledge-based strategies for multi-agent teams playing against nature

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

    Författare :Sam Maltin; Simon Rosén; [2023]
    Nyckelord :;

    Sammanfattning : Analogous to how the Knowledge-Based Subset Construct (KBSC) can transform games of imperfect information against nature into games of perfect information, making it easier to find winning strategies for objectives in these games, the multi-agent knowledge-based subset construct (MKBSC) can be used to find winning strategies in multi-agent games of imperfect information. The difference between the two algorithms is that the generalized version can be applied multiple times, which is interpreted as the agent’s considering not just their own knowledge of the game, but also their knowledge of the other agents, and the knowledge of the other agent’s knowledge about their own knowledge, etc. LÄS MER

  5. 9. Strategy Synthesis for Multi-Agent Games of Imperfect Information

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

    Författare :Andres Guerrero Rodriguez; Rahnama Safdari; [2023]
    Nyckelord :;

    Sammanfattning : This project focuses on strategy synthesis for multi-agent games of imperfect information. The aim ofthis project is to identify strategies for two games of interest. We utilize a program from a previousbachelor thesis to transform the games. LÄS MER

  7. 10. Modeling Real Life Situations as Multi-Agent Games with Imperfect Information Against Nature

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

    Författare :Samin Chowdhury; Elling Morast; [2023]
    Nyckelord :;

    Sammanfattning : Our research explores Multiplayer Games with Imperfect Information, short for ”MAGIIAN”. We specifically focus on two aspects: firstly, identifying real-world problems that can be appropriately modeled as MAGIIANs, and secondly, synthesizing and interpreting strategies for these models using existing tools and algorithms. LÄS MER