Xiao-Long Li

Multi-Agent Reinforcement Learning for Joint Task Offloading and Migration in UAV Swarm Wireless Networks

MAPPO-QM is developed, a multi-agent reinforcement learning method based on Multi-Agent Proximal Policy Optimization that explicitly incorporates queueing dynamics and a rule-based migration mechanism triggered at migration points, indicating that queue-aware task waiting and migration can improve service availability...

Reliable few-label state identification in industrial multivariate time series using prototypical contrastive learning