A Pursuit Strategy for Multi-Agent Pursuit-Evasion Game via Multi-Agent Deep Deterministic Policy Gradient Algorithm

This paper studies a classical pursuit-evasion problem. The pursuer attempts to capture the faster evader in a bounded area. The velocity of evader is 1.2 times as fast as the pursuers'. All of them have adaptive strategies. We use game theory to model the multi-agent pursuit-evasion game and p...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings of ... IEEE International Conference on Unmanned Systems (Online) S. 418 - 423
Hauptverfasser: Ye, Jianfeng, Wang, Qing, Ma, Bei, Wu, Yongbao, Xue, Lei
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 28.10.2022
Schlagworte:
Adaptation models
adaptive strategy
Convergence
Games
MADDPG
multi-agent
Nash equilibrium
Neural networks
Training
ISSN:2771-7372
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper studies a classical pursuit-evasion problem. The pursuer attempts to capture the faster evader in a bounded area. The velocity of evader is 1.2 times as fast as the pursuers'. All of them have adaptive strategies. We use game theory to model the multi-agent pursuit-evasion game and prove that the game model has Nash equilibrium. Then, we modify the multi-agent deep deterministic policy gradient (MADDPG) algorithm for seeking the Nash equilibrium. The simulation examples are given to illustrate the effectiveness of the designed method.
ISSN:2771-7372
DOI:10.1109/ICUS55513.2022.9986838