Co-DQL, a combination of double Q-learning, UCB exploration, mean field modeling, and local reward/state sharing, reduces simulated traffic delays relative to several MARL baselines.
Traffic signal timing optimisation based on genetic algorithm approach, including drivers routing,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learning
Co-DQL, a combination of double Q-learning, UCB exploration, mean field modeling, and local reward/state sharing, reduces simulated traffic delays relative to several MARL baselines.