Distilling deep neural networks with reinforcement learning.
You HuangYuanlong YuPublished in: ICIA (2018)
Keyphrases
- neural network
- reinforcement learning
- function approximators
- function approximation
- model free
- artificial neural networks
- pattern recognition
- learning classifier systems
- temporal difference
- learning algorithm
- fuzzy logic
- feed forward
- reinforcement learning algorithms
- neural network model
- fault diagnosis
- optimal policy
- multi agent
- genetic algorithm
- learning rules
- action selection
- transfer learning
- fuzzy systems
- multi layer
- learning capabilities
- state space
- multilayer perceptron
- feedforward neural networks
- robotic control
- activation function
- network architecture
- optimal control
- back propagation
- artificial intelligence
- machine learning