Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity.
Laixi ShiYuejie ChiPublished in: CoRR (2022)
Keyphrases
- sample complexity
- reinforcement learning
- learning problems
- pac learning
- learning algorithm
- theoretical analysis
- supervised learning
- vc dimension
- lower bound
- robust optimization
- upper bound
- sample size
- active learning
- concept classes
- sequential decision problems
- pac learnability
- training examples
- multi agent
- generalization error
- optimal policy
- irrelevant features
- sample complexity bounds
- number of irrelevant features
- knn