Model-Free Reinforcement Learning: from Clipped Pseudo-Regret to Sample Complexity.
Zihan ZhangYuan ZhouXiangyang JiPublished in: CoRR (2020)
Keyphrases
- sample complexity
- model free reinforcement learning
- lower bound
- upper bound
- reinforcement learning
- theoretical analysis
- learning problems
- pac learning
- supervised learning
- learning algorithm
- special case
- generalization error
- active learning
- worst case
- policy gradient
- sample size
- loss function
- training examples
- np hard
- data sets
- reward function
- average case
- machine learning
- kernel methods
- small number
- computational complexity
- optimal solution