Improving Reinforcement Learning in Stochastic {RAM}-Based Neural Networks.
Alistair FergusonHamid BolouriPublished in: Neural Process. Lett. (1996)
Keyphrases
- neural network
- reinforcement learning
- direct policy search
- stochastic approximation
- learning capabilities
- artificial neural networks
- design considerations
- function approximation
- pattern recognition
- function approximators
- fuzzy logic
- temporal difference
- learning algorithm
- evolutionary learning
- hopfield neural network
- learning automata
- state space
- model free
- back propagation
- fault diagnosis
- stochastic programming
- dynamic programming
- stochastic model
- reinforcement learning algorithms
- markov decision processes
- learning rules
- activation function
- self organizing maps
- recurrent neural networks
- feed forward
- neural network model
- training process
- continuous state spaces
- temporal difference learning
- genetic algorithm
- machine learning