@inproceedings{1bfeee0c305f4eed86f8ac76a4844439,
title = "Off-policy model-based learning under unknown factored dynamics",
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.",
author = "Assaf Hallak and Francois Schnitzler and Timothy Mann and Shie Mannor",
note = "Funding Information: This Research was supported in part by the Israel Science Foundation (grant No. 920/12) and by the European Research Council under the European Union's Seventh Framework Programme (FP/2007-2013)/ERC Grant Agreement n.306638.; 32nd International Conference on Machine Learning, ICML 2015 ; Conference date: 06-07-2015 Through 11-07-2015",
year = "2015",
language = "الإنجليزيّة",
series = "32nd International Conference on Machine Learning, ICML 2015",
pages = "711--719",
editor = "Francis Bach and David Blei",
booktitle = "32nd International Conference on Machine Learning, ICML 2015",
}