A reinforcement learning approach to convoy scheduling on a contested transportation network.
Daniel StimpsonRajesh GanesanPublished in: Optim. Lett. (2015)
Keyphrases
- transportation networks
- reinforcement learning
- moving object trajectories
- road network
- travel time
- traveling salesman problem
- scheduling problem
- scheduling algorithm
- function approximation
- travel cost
- shortest path
- location based services
- machine learning
- trajectory data
- moving objects
- optimal policy
- model free
- spatial networks
- state space
- neural network
- markov decision processes
- spatial data
- computer vision
- learning algorithm
- traffic conditions
- dynamic programming