Year: 2025
Type: preprint
Abstract: We study the statistical complexity of offline decision-making with function approximation, establishing (near) minimax-optimal rates for stochastic contextual bandits and Markov decision processes. The performance limits are captured by the pseudo-dimension of the (value) function class and a new characterization of the behavior policy that \emph{strictly} subsumes all the previous notions of data coverage in the offline decision-making literature. In addition, we seek to understand the benefits of using offline data in online decision-making and show nearly minimax-optimal rates in a wide range of regimes.
Source: arXiv (Cornell University)
Authors: Nguyen-Tang, Thanh, Arora, Raman
Institutions: Johns Hopkins University, Johns Hopkins Medicine
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: green
OpenAlex ID: W6967060480
Cites:
Cited by:
Related to: