Reinforcement Learning for Online Dispatching Policy in Real-Time Train Timetable Rescheduling.
Peng YueYaochu JinXuewu DaiZhen-Hua FengDongliang CuiPublished in: IEEE Trans. Intell. Transp. Syst. (2024)
Keyphrases
- real time
- reinforcement learning
- optimal policy
- policy search
- robotic control
- shop floor
- control policy
- function approximation
- low cost
- machine learning
- policy iteration
- markov decision process
- action selection
- online learning
- approximate dynamic programming
- model free
- policy gradient
- partially observable environments
- control system
- timetabling problem
- rl algorithms
- control policies
- exploration exploitation tradeoff
- production scheduling
- function approximators
- temporal difference
- manufacturing systems
- vision system
- simulated annealing
- state space
- mobile robot
- dynamic programming