Optimal Actor-Critic Policy with Optimized Training Datasets.
Chayan BanerjeeZhiyong ChenNasimul NomanMohsen ZamaniPublished in: CoRR (2021)
Keyphrases
- actor critic
- training dataset
- optimal control
- policy gradient
- approximate dynamic programming
- reinforcement learning
- average reward
- dynamic programming
- policy gradient methods
- temporal difference
- training data
- neuro fuzzy
- optimal policy
- policy iteration
- gradient method
- machine learning
- function approximation
- finite state
- training set
- optimal solution
- feature selection