Hierarchical Dialogue Policy Learning using Flexible State Transitions and Linear Function Approximation.
Heriberto CuayáhuitlIvana Kruijff-KorbayováNina DethlefsPublished in: COLING (Demos) (2012)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- learning tasks
- state transitions
- temporal difference learning algorithms
- temporal difference learning
- learning algorithm
- state transition
- reinforcement learning problems
- temporal difference methods
- supervised learning
- active learning
- policy gradient
- actor critic
- td learning
- neural network
- input output
- radial basis function
- temporal difference
- action space
- support vector machine
- feature extraction