Reinforcement learning based on modular fuzzy model with gating unit.
Toshihiko WatanabeTatsuya WadaPublished in: SMC (2008)
Keyphrases
- fuzzy model
- reinforcement learning
- fuzzy modeling
- takagi sugeno
- input output
- membership functions
- nonlinear systems
- fuzzy clustering
- fuzzy rules
- fuzzy systems
- fuzzy inference
- rule base
- function approximation
- fuzzy sets
- parameter identification
- reinforcement learning algorithms
- fuzzy controller
- initial values
- optimal policy
- state space
- computational intelligence
- optimal control
- fuzzy logic
- fuzzy inference system
- dynamic programming
- information granulation
- real time
- controller design
- model free
- markov decision processes
- learning algorithm
- neural network