-Regularized Temporal-Difference Prediction With Gradient Correction.
Luntong LiDazi LiTianheng SongXin XuPublished in: IEEE Trans. Neural Networks Learn. Syst. (2018)
Keyphrases
- temporal difference
- td learning
- evaluation function
- function approximation
- reinforcement learning
- monte carlo
- model free
- policy evaluation
- temporal difference learning
- step size
- action selection
- policy iteration
- reinforcement learning algorithms
- function approximators
- radial basis function
- data sets
- learning tasks
- linear combination
- active learning
- actor critic
- objective function
- temporal difference methods