Function approximation for large markov decision processes using self-organizing neural networks.
Teck-Hou TengPublished in: IJCNN (2015)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- radial basis function
- temporal difference
- learning tasks
- model free
- temporal difference learning
- temporal difference methods
- function approximators
- pattern recognition
- evolutionary algorithm
- dynamic programming
- markov random field
- data mining
- td learning
- mackey glass