This paper explores the application of multi-agent reinforcement learning in collaborative observation path planning of marine environment observation network. In order to solve the problem of intelligent collaborative observation path in marine environment observation network, we improved the multi-agent reinforcement learning method based on value function. By decomposing the joint action-value functions into a single action-value functions, this method makes full use of the advantages of centralized training and completely decentralized implementation of the learned strategies. The data assimilation results show that the information collected from the path planned by this method can effectively improve the prediction accuracy of the marine environment numerical prediction system.
Multi-agent Reinforcement Learning for Cooperative Observation Path Planning of Ocean Mobile Observation Network
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Kapitel : 228 ; 2309-2317
18.03.2022
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Wave glider winch for ocean profile observation and ocean mobile observation system
Europäisches Patentamt | 2024
|Multi-UAV Path Planning and Following Based on Multi-Agent Reinforcement Learning
DOAJ | 2024
|