skip to main content
Explore Scholarly Publications and Datasets in the NSF-PAR

  • Home
  • Search Results
  • Page 1 of 1

Search for: All records

Creators/Authors contains: "Brunskill, E"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. ; ; ; ; ; ( , Neural Information Processing Systems)
    Free, publicly-accessible full text available December 1, 2022
  2. ; ; ( , International Conference on Artificial Intelligence and Statistics (AISTATS))
    We study the problem of estimating the expected reward of the optimal policy in the stochastic disjoint linear bandit setting. We prove that for certain settings it is possible to obtain an accurate estimate of the optimal policy value even with a number of samples that is sublinear in the number that would be required to find a policy that realizes a value close to this optima. We establish nearly matching information theoretic lower bounds, showing that our algorithm achieves near optimal estimation error. Finally, we demonstrate the effectiveness of our algorithm on joke recommendation and cancer inhibition dosage selectionmore »problems using real datasets.« less
    Accepted Manuscript Full Text Available
  3. ; ; ; ; ( , International Conference on Machine Learning)
    Accepted Manuscript Full Text Available
  4. ; ; ; ; ; ; ( , Advances in neural information processing systems)
    Accepted Manuscript Full Text Available