A Deep Reinforcement Learning Approach for Constrained Online Logistics Route Assignment.

Hao Zeng Yangdong Liu Dandan Zhang Kunpeng Han Haoyuan Hu

Published in: CoRR (2021)

Keyphrases

reinforcement learning
function approximation
online learning
balancing exploration and exploitation
real time
machine learning
supply chain
learning algorithm
state space
markov decision processes
road network
temporal difference learning