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