Shifting Attention Using a Temporal Difference Prediction Error and High-Dimensional Input.
William H. AlexanderPublished in: Adapt. Behav. (2007)
Keyphrases
- prediction error
- temporal difference
- high dimensional
- td learning
- function approximation
- reinforcement learning
- evaluation function
- monte carlo
- step size
- temporal difference methods
- action selection
- motion vectors
- inter frame
- reinforcement learning algorithms
- policy iteration
- bit rate
- model free
- data sets
- reversible watermarking
- nearest neighbor
- policy evaluation
- data points
- supervised learning
- function approximators
- learning algorithm