Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks.
Zihao LiXiang JiMinshuo ChenMengdi WangPublished in: CoRR (2023)
Keyphrases
- sample complexity
- policy evaluation
- learning algorithm
- theoretical analysis
- vc dimension
- generalization error
- learning problems
- upper bound
- least squares
- supervised learning
- temporal difference
- active learning
- special case
- model free
- reinforcement learning
- lower bound
- monte carlo
- markov decision processes
- function approximation
- variance reduction
- training examples
- training samples
- policy iteration
- semi parametric
- data mining