Reinforcement learning with internal expectation for the random neural network.
Ugur HaliciPublished in: Eur. J. Oper. Res. (2000)
Keyphrases
- neural network
- reinforcement learning
- function approximation
- function approximators
- learning capabilities
- fuzzy logic
- back propagation
- reinforcement learning algorithms
- dynamic programming
- artificial neural networks
- pattern recognition
- feed forward
- model free
- fuzzy neural network
- learning process
- neural network model
- backpropagation neural network
- markov decision processes
- robotic control
- state space
- neural network is trained
- optimal policy
- learning algorithm
- bp neural network
- neural nets
- internal and external
- multi layer perceptron
- image reconstruction from projections
- data sets
- feed forward neural networks
- fermentation process
- multi agent reinforcement learning
- uniformly distributed
- temporal difference
- action selection
- hidden layer
- prediction model
- recurrent neural networks
- learning problems
- dynamical systems
- supervised learning
- genetic algorithm
- machine learning