A model-free PID tuning to slosh control using simultaneous perturbation stochastic approximation.
Mohd Ashraf AhmadM. A. RohaniRaja Mohd Taufika Raja IsmailMohd Falfazli Mat JusofM. H. SuidAhmad Nor Kasruddin NasirPublished in: ICCSCE (2015)
Keyphrases
- model free
- stochastic approximation
- policy iteration
- reinforcement learning
- control system
- control method
- impedance control
- function approximation
- proportional integral derivative
- temporal difference
- monte carlo
- reinforcement learning algorithms
- pid controller
- rl algorithms
- optimal control
- control algorithm
- pid control
- finite state
- fuzzy pid
- temporal difference learning
- fuzzy logic controller
- control strategy
- neural network
- markov decision processes
- least squares
- control scheme
- adaptive control
- support vector
- machine learning
- average reward
- learning experience
- optimal policy
- linear programming
- training data