Sökning: "Akib Khan"

Hittade 1 uppsats innehållade orden Akib Khan.

1. 1. Scalable Deep Reinforcement Learning for a Multi-Agent Warehouse System

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

   Författare :Akib Khan; Marcus Loberg; [2022]
   Nyckelord :Reinforcement learning; Deep Q Networks; Neural Network; Scalability; Multi-Agents; Warehouse Environment;

   Sammanfattning : This report presents an application of reinforcementlearning to the problem of controlling multiple robots performingthe task of moving boxes in a warehouse environment. The robotsmake autonomous decisions individually and avoid colliding witheach other and the walls of the warehouse. LÄS MER