A fuzzy Actor-Critic reinforcement learning network.
Xuesong WangYuhu ChengJian-Qiang YiPublished in: Inf. Sci. (2007)
Keyphrases
- actor critic
- reinforcement learning
- temporal difference
- policy gradient
- reinforcement learning algorithms
- approximate dynamic programming
- optimal control
- policy iteration
- neuro fuzzy
- function approximation
- lyapunov stability
- gradient method
- fuzzy rules
- state space
- fuzzy sets
- markov decision processes
- machine learning
- policy gradient methods
- fuzzy controller
- multi agent
- decision making
- learning algorithm
- model free
- step size
- control problems
- dynamical systems
- fuzzy logic
- dynamic programming
- artificial neural networks