Robust multi-objective learning with mentor feedback

Alekh Agarwal, Ashwinkumar Badanidiyuru, Miroslav Dudík, Robert E. Schapire, Aleksandrs Slivkins

Research output: Contribution to journalConference articlepeer-review

2 Scopus citations

Abstract

We study decision making when each action is described by a set of objectives, all of which are to be maximized. During the training phase, we have access to the actions of an outside agent ("mentor"). In the test phase, our goal is to maximally improve upon the mentor's (unobserved) actions across all objectives. We present an algorithm with a vanishing regret compared with the optimal possible improvement, and show that our regret bound is the best possible. The bound is independent of the number of actions, and scales only as the logarithm of the number of objectives.

Original languageEnglish (US)
Pages (from-to)726-741
Number of pages16
JournalJournal of Machine Learning Research
Volume35
StatePublished - 2014
Externally publishedYes
Event27th Conference on Learning Theory, COLT 2014 - Barcelona, Spain
Duration: Jun 13 2014Jun 15 2014

All Science Journal Classification (ASJC) codes

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Statistics and Probability

Keywords

  • Apprenticeship learning
  • Multi-objective learning
  • Random matrix games

Fingerprint

Dive into the research topics of 'Robust multi-objective learning with mentor feedback'. Together they form a unique fingerprint.

Cite this