Deep reinforcement learning method for POMDP based tram signal priority.

Qianxue Tang Lin Zhang Dong Li Zibo Ouyang Wei Zheng

Published in: ITSC (2023)

Keyphrases

reinforcement learning
detection method
dynamic programming
high accuracy
clustering method
pairwise
significant improvement
cost function
preprocessing
similarity measure
computational complexity
markov decision processes
frequency domain
segmentation method
convergence rate
wavelet analysis
policy evaluation