A Routing Optimization Policy Using Graph Convolution Deep Reinforcement Learning.
Yongan GuoQingpeng WuHao ShePublished in: ICCC (2023)
Keyphrases
- reinforcement learning
- optimal policy
- policy search
- state space
- markov decision process
- graph representation
- logistics distribution
- optimization problems
- partially observable environments
- action space
- graph model
- action selection
- global optimization
- partially observable
- reinforcement learning algorithms
- directed graph
- random walk
- image processing
- graph matching
- optimal control
- function approximators
- optimization method
- decision problems
- policy gradient
- vehicle routing
- state and action spaces
- weighted graph
- partially observable markov decision processes
- temporal difference
- model free
- graph mining
- machine learning
- routing algorithm
- markov decision processes
- structured data
- wireless networks
- learning algorithm