Reinforcement learning in continuous state space with perceptual aliasing by using complex-valued RBF network.
Takeshi ShibuyaHideaki AritaTomoki HamagamiPublished in: SMC (2010)
Keyphrases
- perceptual aliasing
- reinforcement learning
- rbf network
- continuous state spaces
- state space
- learning algorithm
- radial basis function
- action space
- activation function
- real valued
- rbf neural network
- function approximation
- back propagation
- markov decision processes
- basis functions
- learning process
- machine learning
- multilayer perceptron
- optimal control
- supervised learning
- dynamic programming
- learning tasks
- transfer learning
- adaptive control
- dynamical systems
- bp neural network
- machine learning algorithms
- learning rate
- support vector machine svm
- control system
- artificial neural networks