Sökning: "Minghua Lu"

Hittade 1 uppsats innehållade orden Minghua Lu.

  1. 1. Distributed Optimization Through Deep Reinforcement Learning

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

    Författare :Mikaela Funkquist; Minghua Lu; [2020]
    Nyckelord :Reinforcement learning; Q-learning; Deep Q-learning; Artificial neural networks; robots; warehouse; agent;

    Sammanfattning : Reinforcement learning methods allows self-learningagents to play video- and board games autonomously. Thisproject aims to study the efficiency of the reinforcement learningalgorithms Q-learning and deep Q-learning for dynamical multi-agent problems. The goal is to train robots to optimally navigatethrough a warehouse without colliding. LÄS MER