Conservative Q-learning with offline multi-agent training improves simulated radio resource scheduling, and centralized training with decentralized execution gives the best complexity-performance trade-off.
ITLinQ+: An improved spectrum sharing mech- anism for device-to-device communications,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.MA 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
An Offline Multi-Agent Reinforcement Learning Framework for Radio Resource Management
Conservative Q-learning with offline multi-agent training improves simulated radio resource scheduling, and centralized training with decentralized execution gives the best complexity-performance trade-off.