Sökning: "multi-agent collaboration"

Hittade 5 uppsatser innehållade orden multi-agent collaboration.

  1. 1. Training Multi-Agent Collaboration using Deep Reinforcement Learning in Game Environment

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

    Författare :Jie Deng; [2018]
    Nyckelord :Deep Reinforcement Learning; deep neural networks; multi-agent collaboration; games;

    Sammanfattning : Deep Reinforcement Learning (DRL) is a new research area, which integrates deep neural networks into reinforcement learning algorithms. It is revolutionizing the field of AI with high performance in the traditional challenges, such as natural language processing, computer vision etc. LÄS MER

  3. 2. Simultaneous coalition formation and task assignment in a real-time strategy game

    Master-uppsats, Linköpings universitet/Artificiell intelligens och integrerade datorsystem

    Författare :Fredrik Präntare; [2017]
    Nyckelord :;

    Sammanfattning : In this thesis we present an algorithm that is designed to improve the collaborative capabilities of agents that operate in real-time multi-agent systems. Furthermore, we study the coalition formation and task assignment problems in the context of real-time strategy games. LÄS MER

  4. 3. Multi-agent autonomous target tracking using distance-based formations

    Master-uppsats, KTH/Reglerteknik

    Författare :Rasmus Ringbäck; [2017]
    Nyckelord :;

    Sammanfattning : In this thesis, the problem of cooperative control of a system of autonomous agents for targettracking is studied, with special focus on autonomous surface vehicles and minimizing theenergy usage in the system. By separating the control problem into two different parts, weindependently calculate the coordination scheme of the system using virtual agents withsingle integrator dynamics and design the control of the actual agents to follow the virtual. LÄS MER

  5. 4. Collaboration in Multi-agent Games : Synthesis of Finite-state Strategies in Games of Imperfect Information

    Master-uppsats, KTH/Skolan för datavetenskap och kommunikation (CSC)

    Författare :Edvin Lundberg; [2017]
    Nyckelord :Multi-agent games; multiagent games; multi-agent system; imperfect information; imperfect recall; collaboration; imperfect communication; finite-state strategy; concurrent games; concurrent system; strategy synthesis; strategy construction; automated programming; automated problem solving; automated collaboration; verification; knowledge-based subset construction; knowledge tracking;

    Sammanfattning : We study games where a team of agents needs to collaborate against an adversary to achieve a common goal. The agents make their moves simultaneously, and they have different perceptions about the system state after each move, due to different sensing capabilities. LÄS MER

  7. 5. Automatic Planning of Collaborating Autonomous Unmanned Aerial Vehicles

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

    Författare :Joakim Kareliusson; [2016]
    Nyckelord :;

    Sammanfattning : Collaboration between autonomous robots allows for complex mission to be executed more eciently.A collaborative mission typically consists of a number of robots and tasks where the robots havedierent roles and need cooperatively assign the tasks to the team resulting in a faster overall missionexecution time. LÄS MER