Multi-agent deep RL enables distributed link scheduling that improves both average and 5th percentile throughput, approaching centralized performance and remaining robust to network density changes.
Deep reinforcement learning with double Q-learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
When Multiple Agents Learn to Schedule: A Distributed Radio Resource Management Framework
Multi-agent deep RL enables distributed link scheduling that improves both average and 5th percentile throughput, approaching centralized performance and remaining robust to network density changes.