Variance Reduced Policy Evaluation with Smooth Function Approximation.
Hoi-To WaiMingyi HongZhuoran YangZhaoran WangKexin TangPublished in: NeurIPS (2019)
Keyphrases
- function approximation
- policy evaluation
- temporal difference
- variance reduction
- reinforcement learning
- model free
- td learning
- learning tasks
- radial basis function
- reinforcement learning algorithms
- function approximators
- least squares
- monte carlo
- machine learning
- markov decision processes
- supervised learning
- naive bayes classifier
- policy iteration
- semi parametric
- knn
- data mining