Coordinated Multi-Agent Reinforcement Learning for Unmanned Aerial Vehicle Swarms in Autonomous Mobile Access Applications
This addresses coordination challenges for UAV swarms in mobile access applications, but appears incremental as it builds on existing CTDE frameworks.
The paper tackles the problem of controlling multiple unmanned aerial vehicles (UAVs) for autonomous mobile access by proposing a centralized training and distributed execution (CTDE)-based multi-agent deep reinforcement learning (MADRL) method, which maximizes total quality of service (QoS) but does not report specific numerical results.
This paper proposes a novel centralized training and distributed execution (CTDE)-based multi-agent deep reinforcement learning (MADRL) method for multiple unmanned aerial vehicles (UAVs) control in autonomous mobile access applications. For the purpose, a single neural network is utilized in centralized training for cooperation among multiple agents while maximizing the total quality of service (QoS) in mobile access applications.