Deep multi-agent reinforcement learning for resource allocation in NOMA-enabled MEC

Research on offloading strategies for mobile edge computing in ultradense networks

“…Guo et al [9] tackled the offloading problem with a layered genetic algorithm, demonstrating its effectiveness. Addressing the heterogeneity and dynamics of networks, MDP and reinforcement learning methods were widely employed for dynamic resource allocation in network systems [10][11][12][13].…”