Model-Based Actor-Critic with Chance Constraint for Stochastic System.
Baiyu PengYao MuYang GuanShengbo Eben LiYuming YinJianyu ChenPublished in: CDC (2021)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- model free
- policy gradient
- optimal control
- approximate dynamic programming
- policy iteration
- function approximation
- monte carlo
- gradient method
- neuro fuzzy
- average reward
- reinforcement learning algorithms
- kernel methods
- machine learning
- least squares
- decision making