Attention-Gated Reinforcement Learning in Neural Networks - A Unified View.
Tobias BroschFriedhelm SchwenkerHeiko NeumannPublished in: ICANN (2013)
Keyphrases
- neural network
- reinforcement learning
- back propagation
- artificial neural networks
- markov decision processes
- function approximation
- function approximators
- fault diagnosis
- multi agent
- pattern recognition
- learning capabilities
- genetic algorithm
- fuzzy logic
- optimal policy
- multi layer
- neural nets
- autonomous mental development
- least squares
- state space
- transfer learning
- self organizing maps
- decision making
- training process
- learning algorithm
- machine learning
- data mining