机译:A Deep Reinforcement Learning-Based Dynamic Traffic Offloading in Space-Air-Ground Integrated Networks (SAGIN)
Graduate School of Information Sciences (GSIS), Tohoku University, Sendai, Japan;
Information Technology Research and Development Center, Mitsubishi Electric Corporation, Kamakura, Japan;
Reinforcement learning; Heuristic algorithms; Satellites; Proposals; Bandwidth; Channel allocation; Topology; Space-air-ground integrated networks (SAGIN); satellite communication; UAV; traffic offloading; reinforcement learning (RL); double Q-learning;