Essays about: "Multi-agent networks"

Showing result 6 - 10 of 27 essays containing the words Multi-agent networks.

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

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

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

   Abstract : 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. READ MORE

3. 7. Multi Agent Reinforcement Learning for Game Theory : Financial Graphs

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

   Author : Bryan Yu; [2021]
   Keywords : Multi-Agent Reinforcement Learning; Reinforcement Learning; Game Theory; Financial Networks; Financial Graphs; Machine Learning; Financial Graphs; Computational Economics; Multi-Agent Reinforcement Learning; Reinforcement Learning; Game Theory; Financial Networks; Financial Graphs; Machine Learning; Financial Graphs; Computational Economics;

   Abstract : We present the rich research potential at the union of multi agent reinforcement learning (MARL), game theory, and financial graphs. We demonstrate how multiple game theoretic scenarios arise in three node financial graphs with minor modifications. We highlight six scenarios used in this study. READ MORE

4. 8. Warehouse Optimization by Multi-Agent Rollout Algorithms

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

   Author : Laura Briffa; William Emanuelsson; [2021]
   Keywords : multi-agent problems; reinforcement learning; optimization and optimal control; collision avoidance; warehouse;

   Abstract : Systems consisting of multiple robots are traditionallydifficult to optimize. This project considers such a systemin a simulated warehouse setting, where the robots are todeliver boxes while avoiding collisions. Adding such collisionconstraints complicates the problem. READ MORE

5. 9. Interference Aware Distributed Network Formation with Reinforcement Learning

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

   Author : Berkcan Okur; [2021]
   Keywords : distributed; network formation; topology formation; reinforcement learning; multi-agent; distribuerad; nätverksbildning; topologibildning; förstärkande inlärning; multiagent;

   Abstract : Ad-hoc networks suffer from dynamicity due to mobility of the nodes or node addition/removal to/from the system. This means, the formed topology may not be connected anymore or better topologies can be found as time passes if the position of the nodes changes or some nodes in the network is broken. READ MORE

6. 10. Distributed Optimization Through Deep Reinforcement Learning

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

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

   Abstract : 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. READ MORE