MW-MADDPG: a meta-learning based decision-making method for collaborative UAV swarm

Frontiers in Neurorobotics

Neuroscience

Minrui Zhao¹  Gang Wang¹  Tengda Li¹  Xiangke Guo¹  Qiang Fu¹  XiangYu Liu¹  Yu Chen² 

[1] College of Air and Missile Defense, Air Force Engineering University, Xi'an, China;Graduate School, Academy of Military Science, Beijing, China;Unit 95866 of PLA, Baoding, China;

关键词: UAV;    meta learning;    multi-agent reinforcement learning (MARL);    Model Agnostic Meta Learning (MAML);    MADDPG;   

DOI  :  10.3389/fnbot.2023.1243174

 received in 2023-06-20, accepted in 2023-09-04,  发布年份 2023

来源: Frontiers

【 摘 要 】

Unmanned Aerial Vehicles (UAVs) have gained popularity due to their low lifecycle cost and minimal human risk, resulting in their widespread use in recent years. In the UAV swarm cooperative decision domain, multi-agent deep reinforcement learning has significant potential. However, current approaches are challenged by the multivariate mission environment and mission time constraints. In light of this, the present study proposes a meta-learning based multi-agent deep reinforcement learning approach that provides a viable solution to this problem. This paper presents an improved MAML-based multi-agent deep deterministic policy gradient (MADDPG) algorithm that achieves an unbiased initialization network by automatically assigning weights to meta-learning trajectories. In addition, a Reward-TD prioritized experience replay technique is introduced, which takes into account immediate reward and TD-error to improve the resilience and sample utilization of the algorithm. Experiment results show that the proposed approach effectively accomplishes the task in the new scenario, with significantly improved task success rate, average reward, and robustness compared to existing methods.

【 授权许可】

Unknown   
Copyright © 2023 Zhao, Wang, Fu, Guo, Chen, Li and Liu.