Biased Gradient Estimate with Drastic Variance Reduction for Meta Reinforcement Learning.
Yunhao TangPublished in: CoRR (2021)
Keyphrases
- variance reduction
- policy gradient
- gradient estimation
- reinforcement learning
- confidence intervals
- sample size
- monte carlo
- bias variance decomposition
- machine learning
- state space
- function approximation
- learning algorithm
- gradient method
- naive bayes classifier
- reinforcement learning algorithms
- importance sampling
- dynamic programming
- image segmentation
- quasi monte carlo
- generative model
- feature space