controller using Laguerre function approximation.
Marta ZagorowskaJerzy BaranowskiPiotr BaniaWaldemar BauerTomasz DziwinskiPawel PiatekPublished in: MMAR (2015)
Keyphrases
- function approximation
- reinforcement learning
- control system
- temporal difference learning algorithms
- temporal difference learning
- radial basis function
- learning tasks
- model free
- temporal difference
- actor critic
- closed loop
- feedback control
- optimal control
- control scheme
- fuzzy logic controller
- neural network
- temporal difference methods
- fuzzy controller
- control algorithm
- reinforcement learning algorithms
- adaptive control
- linear combination
- function approximators
- control policy
- image classification
- policy gradient
- control method