Breaking the Sample Complexity Barrier to Regret-Optimal Model-Free Reinforcement Learning.
Gen LiLaixi ShiYuxin ChenYuantao GuYuejie ChiPublished in: CoRR (2021)
Keyphrases
- sample complexity
- lower bound
- worst case
- upper bound
- pac learning
- active learning
- learning problems
- vc dimension
- model free reinforcement learning
- theoretical analysis
- generalization error
- supervised learning
- dynamic programming
- training examples
- special case
- irrelevant features
- sample size
- learning algorithm
- objective function
- decision trees