Interactive Learning with Corrective Feedback for Policies Based on Deep Neural Networks.
Rodrigo Pérez-DattariCarlos CeleminJavier Ruiz-del-SolarJens KoberPublished in: ISER (2018)
Keyphrases
- interactive learning
- neural network
- pattern recognition
- interactive video
- computer technology
- back propagation
- optimal policy
- genetic algorithm
- competitive learning
- feed forward
- neural network model
- fuzzy logic
- artificial neural networks
- self organizing maps
- neural nets
- database systems
- deep learning
- cellular neural networks
- decision making
- activation function
- neural network is trained