Uncertainty and Trust Estimation in Incrementally Learning Function Approximation.
Andreas BuschermöhleJan H. SchoenkeWerner BrockmannPublished in: IPMU (1) (2012)
Keyphrases
- function approximation
- reinforcement learning
- learning tasks
- td learning
- temporal difference learning
- learning algorithm
- learning process
- function approximators
- temporal difference methods
- active learning
- temporal difference
- actor critic
- evaluation function
- temporal difference learning algorithms
- data sets
- decision trees
- neural network