Essays about: "Multi-agent networks"

Showing result 1 - 5 of 15 essays containing the words Multi-agent networks.

  1. 1. Distributed Optimisation in Multi-Agent Systems Through Deep Reinforcement Learning

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS); KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Andreas Eriksson; Jonas Hansson; [2019]
    Keywords : Reinforcement learning; distributed; optimisation; Q-learning; deep Q-learning; warehouse robots; artificial neural networks.;

    Abstract : The increased availability of computing power have made reinforcement learning a popular field of science in the most recent years. Recently, reinforcement learning has been used in applications like decreasing energy consumption in data centers, diagnosing patients in medical care and in text-tospeech software. READ MORE

  2. 2. Autonomous control of unmanned aerial multi-agent networks in confined spaces

    University essay from Lunds universitet/Institutionen för reglerteknik

    Author : Sebastian Green; Pontus Månsson; [2019]
    Keywords : Technology and Engineering;

    Abstract : In this thesis, the functionality of existing Crazyflie models is extended to include current implementations of attitude and velocity control. The models are validated both as individual agents and as a swarm through comparisons of swarm behaviour during step, ramp and frequency response testing. READ MORE

  3. 3. Topology optimization for distributed consensus in multi-agent networks

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : Johan Niklasson; Oskar Hahr; [2019]
    Keywords : Multi-agent networks; Distributed systems; Wireless Sensor Network; Consensus averaging; Unmanned Aerial Vehicle; Graph-Theory.; Multiagent-nätverk; Distribuerade system; Trådlösa sensornätverk; Konsensusvärde; Drönare; Grafteori.;

    Abstract : Distributed networks, meaning a network in which several agents work together unanimously to perform some task in order to reach goals has become a field with a wide range of applications. One such applications may exist in the form of drones with a purpose of observing and detecting forest fires. READ MORE

  4. 4. Drones without a master : Resource efficiency in consensus-reaching topologies

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS); KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Author : John Björkman Nilsson; Jonatan Cervall; [2019]
    Keywords : ;

    Abstract : In this study we have compared five different heuristic algorithms for adding edges to existing graphs with the goal of improving convergence rate for reaching consensus. This while keeping the cost of adding edges, and thus sending more signals, in mind. READ MORE

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

    University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)

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

    Abstract : 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. READ MORE