An Improved Convergence Analysis of Stochastic Variance-Reduced Policy Gradient.
Pan XuFelicia GaoQuanquan GuPublished in: UAI (2019)
Keyphrases
- convergence analysis
- policy gradient
- model free reinforcement learning
- approximation methods
- variance reduction
- monte carlo
- global convergence
- reinforcement learning
- optimality conditions
- convergence rate
- gradient method
- reinforcement learning algorithms
- function approximation
- sample size
- step size
- optimal control
- partially observable markov decision processes
- supervised learning
- cost function
- search algorithm
- machine learning