Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation

View Researcher's Other Codes

Disclaimer: The provided code links for this paper are external links. Science Nest has no responsibility for the accuracy, legality or content of these links. Also, by downloading this code(s), you agree to comply with the terms of use as set out by the author(s) of the code(s).

Please contact us in case of a broken link from here

Authors Qiang Liu, Ziyang Tang, Dengyong Zhou, Lihong Li
Journal/Conference Name NeurIPS 2018 12
Paper Category
Paper Abstract We consider the off-policy estimation problem of estimating the expected reward of a target policy using samples collected by a different behavior policy. Importance sampling (IS) has been a key technique to derive (nearly) unbiased estimators, but is known to suffer from an excessively high variance in long-horizon problems. In the extreme case of in infinite-horizon problems, the variance of an IS-based estimator may even be unbounded. In this paper, we propose a new off-policy estimation method that applies IS directly on the stationary state-visitation distributions to avoid the exploding variance issue faced by existing estimators.Our key contribution is a novel approach to estimating the density ratio of two stationary distributions, with trajectories sampled from only the behavior distribution. We develop a mini-max loss function for the estimation problem, and derive a closed-form solution for the case of RKHS. We support our method with both theoretical and empirical analyses.
Date of publication 2018
Code Programming Language Python
Comment

Copyright Researcher 2021