CTD: Cascaded Temporal Difference Learning for the Mean-Standard Deviation Shortest Path Problem.
Hongliang GuoXuejie HouQihang PengPublished in: IEEE Trans. Intell. Transp. Syst. (2022)
Keyphrases
- standard deviation
- shortest path problem
- temporal difference learning
- shortest path
- fixed point
- function approximation
- reinforcement learning
- game playing
- evaluation function
- combinatorial optimization problems
- multiple objectives
- temporal difference
- correlation coefficient
- directed graph
- markov decision process
- directed acyclic graph
- reinforcement learning algorithms
- neural network
- sufficient conditions
- machine learning
- radial basis function
- worst case
- probabilistic model
- model free
- multi objective
- bayesian networks