EconBase
← All papers

On Well-posedness and Minimax Optimal Rates of Nonparametric Q-function Estimation in Off-policy Evaluation

Xiaohong Chen, Zhengling Qi

arXiv 17 Jan 2022 · Mathematics — Statistics Theory · 5 citations (OpenAlex)

arXiv:2201.06169 · PDF · DOI · OpenAlex · Extracted main text

Abstract

We study the off-policy evaluation (OPE) problem in an infinite-horizon Markov decision process with continuous states and actions. We recast the $Q$-function estimation into a special form of the nonparametric instrumental variables (NPIV) estimation problem. We first show that under one mild condition the NPIV formulation of $Q$-function estimation is well-posed in the sense of $L^2$-measure of ill-posedness with respect to the data generating distribution, bypassing a strong assumption on the discount factor $\gamma$ imposed in the recent literature for obtaining the $L^2$ convergence rates of various $Q$-function estimators. Thanks to this new well-posed property, we derive the first minimax lower bounds for the convergence rates of nonparametric estimation of $Q$-function and its derivatives in both sup-norm and $L^2$-norm, which are shown to be the same as those for the classical nonparametric regression (Stone, 1982). We then propose a sieve two-stage least squares estimator and establish its rate-optimality in both norms under some mild conditions. Our general results on the well-posedness and the minimax lower bounds are of independent interest to study not only other nonparametric estimators for $Q$-function but also efficient estimation on the value of any target policy in off-policy settings.

Citation extraction

57
references
144
in-text mentions
63
distinct cited
2
self-citations
10,878
main-text words

appendix boundary found by appendix_command · 57% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Blundell, Chen \ Kristensen (2007) `Semi-nonparametric iv estimation of shape-invariant engel curves', Econometrica 75(6), 1613–16691.00073100%
2Farahmand, Ghavamzadeh, Szepesvári \ Mannor (2016) `Regularized policy iteration with nonparametric function spaces', The Journal of Machine Learning Research 17(1), 4809–48741.00063100%
3Kallus \ Uehara (2019) `Efficiently breaking the curse of horizon: Double reinforcement learning in infinite-horizon processes', arXiv preprint arXiv:1…1.00053100%
4Stone (1982) `Optimal global rates of convergence for nonparametric regression', The Annals of Statistics pp. 1040–10530.92844100%
5Shi, Zhang, Lu \ Song (2020) `Statistical inference of the value function for reinforcement learning in infinite horizon settings', Journal of the Royal Stat…0.874112100%
6Uehara, Imaizumi, Jiang, Kallus, Sun \ Xie (2021) `Finite sample analysis of minimax offline reinforcement learning: Completeness, fast rates and first-order efficiency', arXiv p…0.87452100%
7Jin, Yang \ Wang (2021) Is pessimism provably efficient for offline rl?, in `International Conference on Machine Learning', PMLR, pp. 5084–50960.84333100%
8Chen \ Christensen (2018) `Optimal sup-norm rates and uniform inference on nonlinear functionals of nonparametric IV regression', Quantitative Economics 9…0.75916944%
9Chen \ Christensen (2015) `Optimal uniform convergence rates and asymptotic normality for series estimators under weak dependence and weak conditions', Jo…0.7547543%
10Huang et al (1998) `Projection estimation in multiple regression with application to functional anova models', Annals of Statistics 26(1), 242–2720.7373367%

Showing the top 10 of 63 scored citations.

Cited by, within the corpus

arXiv econ.EM papers that cite this one, ranked by how heavily they lean on it.

Citing paperIntensityMentionsSections
1Inference on Time Series Nonparametric Conditional Moment Restrictions Using General Sieves0.73732
2Welfare Analysis in Dynamic Models0.64422
3Adaptive Estimation and Uniform Confidence Bands for Nonparametric Structural Functions and Elasticities0.40511