Sample Complexity of Policy Gradient Finding Second-Order Stationary Points.
Long YangQian ZhengGang PanPublished in: AAAI (2021)
Keyphrases
- sample complexity
- policy gradient
- stationary points
- theoretical analysis
- learning problems
- upper bound
- learning algorithm
- special case
- active learning
- lower bound
- generalization error
- supervised learning
- sample size
- reinforcement learning
- nonlinear programming
- training examples
- learning tasks
- function approximation
- cross validation
- machine learning algorithms
- search space