A neural network-like critic for reinforcement learning.
Hiroshi YamakawaYoichi OkabePublished in: Neural Networks (1995)
Keyphrases
- reinforcement learning
- neural network
- function approximation
- temporal difference
- reinforcement learning algorithms
- actor critic
- function approximators
- back propagation
- policy gradient
- state space
- radial basis function
- neural network model
- fuzzy logic
- model free
- prediction model
- multilayer perceptron
- temporal difference learning
- learning capabilities
- robotic control
- fuzzy neural network
- learning algorithm
- pattern recognition
- artificial neural networks
- neural network is trained
- neural nets
- multi agent
- supervised learning
- machine learning
- recurrent neural networks
- genetic algorithm
- feed forward neural networks
- markov decision processes
- bp neural network
- fault diagnosis
- action selection
- monte carlo
- robot control
- network architecture
- fuzzy artmap
- training algorithm
- learning problems
- feed forward