Reinforcement Learning Method with Dynamic Learning Rate for Real-Time Route Guidance Based on SUMO.

Yuzhen Li Jiawen Tang Han Zhao Ruikang Luo

Published in: ICARCV (2022)

Keyphrases

real time
learning rate
high accuracy
cost function
support vector machine
optimization algorithm
reinforcement learning
objective function
pairwise
support vector machine svm
sensitivity analysis
convergence rate
dynamic programming
particle swarm optimization
convergence speed
error function