Towards Real-Time Routing Optimization with Deep Reinforcement Learning: Open Challenges.
Paul AlmasanJosé Suárez-VarelaBo WuShihan XiaoPere Barlet-RosAlbert Cabellos-AparicioPublished in: HPSR (2021)
Keyphrases
- real time
- reinforcement learning
- robotic control
- key issues
- lessons learned
- function approximation
- logistics distribution
- low cost
- real world
- optimization algorithm
- temporal difference
- control system
- optimization problems
- vision system
- data acquisition
- vehicle routing
- global optimization
- machine learning
- optimization process
- constrained optimization
- optimization methods
- neural network
- action selection
- mobile ad hoc networks
- routing problem
- optimal solution
- routing algorithm
- ad hoc networks
- learning process
- markov decision processes
- high speed