Dynamic Charging Scheme Problem With Actor-Critic Reinforcement Learning.
Meiyi YangNianbo LiuLin ZuoYong FengMing LiuHaigang GongMing LiuPublished in: IEEE Internet Things J. (2021)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- temporal difference
- reinforcement learning algorithms
- approximate dynamic programming
- function approximation
- optimal control
- neuro fuzzy
- dynamic programming
- policy iteration
- machine learning
- dynamic environments
- gradient method
- learning algorithm
- state space
- rl algorithms
- markov decision processes
- least squares
- control problems
- model free
- linear program
- natural actor critic