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.

Our framework applies to a wide range of SMF-type problems for multi-class classification with auxiliary features.

Effective resistances have a broad range of algorithmic implications.

In this paper, we introduce alowrank interaction and sparse additive effects(LORIS) model which combines matrix regression on a dictionary and low-rank design, to estimate main effects andinteractions simultaneously.

Neural Information Processing Systems http://nips.cc/

Specifically,theyreduce theproblem of optimization with a first-order oracle to a mean estimation problem whose probability of error is lowerbounded usingFano'smethod (cf.[31]).