Varying cooperation in SOM for improved function approximation.
Josef GöppertWolfgang RosenstielPublished in: ICNN (1996)
Keyphrases
- function approximation
- reinforcement learning
- self organizing maps
- temporal difference learning algorithms
- temporal difference
- radial basis function
- learning tasks
- temporal difference learning
- function approximators
- neural network
- multi agent
- model free
- input data
- td learning
- high dimensional
- e learning
- reinforcement learning algorithms
- learning algorithm