Skip to yearly menu bar Skip to main content


Poster

On The Statistical Complexity of Offline Decision-Making

Thanh Nguyen-Tang · Raman Arora

Hall C 4-9 #1506
[ ] [ Paper PDF ]
[ Poster
Thu 25 Jul 4:30 a.m. PDT — 6 a.m. PDT

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 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.

Chat is not available.