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.
Cite
Text
Hallak et al. "Off-Policy Model-Based Learning Under Unknown Factored Dynamics." International Conference on Machine Learning, 2015.Markdown
[Hallak et al. "Off-Policy Model-Based Learning Under Unknown Factored Dynamics." International Conference on Machine Learning, 2015.](https://mlanthology.org/icml/2015/hallak2015icml-offpolicy/)BibTeX
@inproceedings{hallak2015icml-offpolicy,
title = {{Off-Policy Model-Based Learning Under Unknown Factored Dynamics}},
author = {Hallak, Assaf and Schnitzler, Francois and Mann, Timothy and Mannor, Shie},
booktitle = {International Conference on Machine Learning},
year = {2015},
pages = {711-719},
volume = {37},
url = {https://mlanthology.org/icml/2015/hallak2015icml-offpolicy/}
}