STCL using G-MAPPO prevents policy stagnation in UAV networks, recovering reliability above 0.9 for up to 100 users and delivering 20% capacity gain under high loads versus MADDPG.
Adapti ve 3d placement of multiple uav-mounted base stations in 6g air borne small cells with deep reinforcement learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Spatiotemporal Continual Learning for Mobile Edge UAV Networks: Mitigating Catastrophic Forgetting
STCL using G-MAPPO prevents policy stagnation in UAV networks, recovering reliability above 0.9 for up to 100 users and delivering 20% capacity gain under high loads versus MADDPG.