Sample Complexity of Policy Gradient Finding Second-Order Stationary Points.
Long YangQian ZhengGang PanPublished in: CoRR (2020)
Keyphrases
- sample complexity
- stationary points
- policy gradient
- theoretical analysis
- learning problems
- lower bound
- supervised learning
- generalization error
- special case
- active learning
- learning algorithm
- upper bound
- sample size
- training examples
- fixed point
- state space
- objective function
- machine learning
- learning tasks
- mathematical programming
- reinforcement learning algorithms
- reinforcement learning
- computational complexity