A two-level DDPG controller that splits a fixed 60-second traffic signal cycle by direction, then by movement, achieves the lowest average travel time among eight methods in CityFlow simulations.
Large-scale traffic signal control using constrained network partition and adaptive deep reinforcement learning,
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.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
A Hierarchical Deep Reinforcement Learning Framework for Traffic Signal Control with Predictable Cycle Planning
A two-level DDPG controller that splits a fixed 60-second traffic signal cycle by direction, then by movement, achieves the lowest average travel time among eight methods in CityFlow simulations.