A split-predictor Dyna-DDPG framework learns queueing-network routing policies in simulation and shows qualitative robustness to single-node blockages and scaling to 100 nodes.
Title resolution pending
1 Pith paper cite this work, alongside 112 external citations. Polarity classification is still indexing.
1
Pith paper citing it
112
external citations · OpenAlex
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Simulation-Driven Reinforcement Learning in Queuing Network Routing Optimization
A split-predictor Dyna-DDPG framework learns queueing-network routing policies in simulation and shows qualitative robustness to single-node blockages and scaling to 100 nodes.