On TD(0) with function approximation: Concentration bounds and a centered variant with exponential convergence.
Nathaniel KordaPrashanth L. A.Published in: ICML (2015)
Keyphrases
- function approximation
- temporal difference
- td learning
- temporal difference learning
- reinforcement learning
- reinforcement learning algorithms
- temporal difference learning algorithms
- policy evaluation
- temporal difference methods
- radial basis function
- model free
- td methods
- convergence rate
- learning tasks
- convergence speed
- function approximators
- neural network
- monte carlo
- e learning