Off-policy model-based learning under unknown factored dynamics

Assaf Hallak, Francois Schnitzler, Timothy Mann, Shie Mannor

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Off-policy learning in dynamic decision problems is essential for providing strong evidence that a new policy is better than the one in use. But how can we prove superiority without testing the new policy? To answer this question, we introduce the G-SCOPE algorithm that evaluates a new policy based on data generated by the existing policy. Our algorithm is both computationally and sample efficient because it greedily learns to exploit factored structure in the dynamics of the environment. We present a finite sample analysis of our approach and show through experiments that the algorithm scales well on high-dimensional problems with few samples.

Original languageEnglish
Title of host publication32nd International Conference on Machine Learning, ICML 2015
EditorsFrancis Bach, David Blei
Pages711-719
Number of pages9
ISBN (Electronic)9781510810587
StatePublished - 2015
Event32nd International Conference on Machine Learning, ICML 2015 - Lile, France
Duration: 6 Jul 201511 Jul 2015

Publication series

Name32nd International Conference on Machine Learning, ICML 2015
Volume1

Conference

Conference32nd International Conference on Machine Learning, ICML 2015
Country/TerritoryFrance
CityLile
Period6/07/1511/07/15

All Science Journal Classification (ASJC) codes

  • Human-Computer Interaction
  • Computer Science Applications

Cite this