Optimal Train Control by Approximate Dynamic Programming: Comparison of Three Value Function Approximation Methods.
Tong LiuJing XunJiateng YinXiao XiaoPublished in: ITSC (2018)
Keyphrases
- approximate dynamic programming
- control policy
- approximation methods
- stochastic dynamic programming
- reinforcement learning
- long run
- function approximators
- average cost
- dynamic programming
- linear program
- optimal control
- step size
- belief state
- machine learning
- temporal difference
- state space
- control system
- decision making