We propose and analyze a reinforcement learning principle that approximates the1 Bellman equations by enforcing their validity only along an user-defined space of2 test functions. Focusing on applications to model-free offline RL with function3 approximation, we exploit this principle to derive confidence intervals for off-policy4 evaluation, as well as to optimize over policies within a prescribed policy class.5 We prove an oracle inequality on our policy optimization procedure in terms of6 a trade-off between the value and uncertainty of an arbitrary comparator policy.7 Different choices of test function spaces allow us to tackle different problems8 within a common framework. We characterize the loss of efficiency in moving9 from on-policy to off-policy data using our procedures, and establish connections10 to concentrability coefficients studied in past work. We examine in depth the11 implementation of our methods with linear function approximation, and provide12 theoretical guarantees with polynomial-time implementations even when Bellman13 closure does not hold.14

Estimation and inference on causal parameters is typically reduced to a generalized method of moments problem, which involves auxiliary functions that correspond to solutions to a regression or classification problem. Recent line of work on debiased machine learning shows how one can use generic machine learning estimators for these auxiliary problems, while maintaining asymptotic normality and root-n consistency of the target parameter of interest, while only requiring mean-squared-error guarantees from the auxiliary estimation algorithms. The literature typically requires that these auxiliary problems are fitted on a separate sample or in a cross-fitting manner. We show that when these auxiliary estimation algorithms satisfy natural leave-one-out stability properties, then sample splitting is not required. This allows for sample re-use, which can be beneficial in moderately sized sample regimes. For instance, we show that the stability properties that we propose are satisfied for ensemble bagged estimators, built via sub-sampling without replacement, a popular technique in machine learning practice.

Post-hoc gradient-based interpretability methods [1, 2] that provide instancespecific explanations of model predictions are often based on assumption (A): magnitude of input gradients--gradients of logits with respect to input--noisily highlight discriminative task-relevant features. In this work, we test the validity of assumption (A) using a three-pronged approach: 1. We develop an evaluation framework, DiffROAR, to test assumption (A) on four image classification benchmarks. Our results suggest that (i) input gradients of standard models (i.e., trained on original data) may grossly violate (A), whereas (ii) input gradients of adversarially robust models satisfy (A) reasonably well.