Stochastic Variance Reduction for Deep Q-learning.
Wei-Ye ZhaoXiya GuanYang LiuXiaoming ZhaoJian PengPublished in: CoRR (2019)
Keyphrases
- variance reduction
- monte carlo
- stochastic approximation
- gradient estimation
- sample size
- bias variance decomposition
- reinforcement learning
- quasi monte carlo
- importance sampling
- random numbers
- function approximation
- state space
- learning algorithm
- markov chain
- confidence intervals
- error rate
- particle filter
- naive bayes classifier
- text mining
- semi supervised
- policy gradient
- video sequences
- image sequences