Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity.
Zihan ZhangYuan ZhouXiangyang JiPublished in: ICML (2021)
Keyphrases
- sample complexity
- model free reinforcement learning
- lower bound
- upper bound
- theoretical analysis
- reinforcement learning
- learning problems
- active learning
- pac learning
- supervised learning
- special case
- worst case
- learning algorithm
- sample size
- generalization error
- policy gradient
- loss function
- training examples
- machine learning algorithms
- objective function
- machine learning
- average case
- decision problems
- unlabeled data
- text mining
- reward function
- support vector