Model-Based Actor-Critic with Chance Constraint for Stochastic System.
Baiyu PengYao MuYang GuanShengbo Eben LiYuming YinJianyu ChenPublished in: CoRR (2020)
Keyphrases
- actor critic
- reinforcement learning
- approximate dynamic programming
- policy gradient
- model free
- temporal difference
- reinforcement learning algorithms
- optimal control
- neuro fuzzy
- monte carlo
- gradient method
- policy iteration
- average reward
- neural network
- learning automata
- function approximation
- function approximators
- step size
- state space
- dynamic programming