A percentile-based reward for DRL-based RAN slicing meets delay-violation probability constraints while cutting average delay by 38% versus an average-delay baseline, and a reward-weighted model personalization method outperforms federated averaging.
Intelligence and learning in o-ran for data-driven nextg cellular networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Percentile-Based Deep Reinforcement Learning and Reward Based Personalization For Delay Aware RAN Slicing in O-RAN
A percentile-based reward for DRL-based RAN slicing meets delay-violation probability constraints while cutting average delay by 38% versus an average-delay baseline, and a reward-weighted model personalization method outperforms federated averaging.