72 citations · 176 across the 14 of their papers we have counts for
14 papers
Source Condition Double Robust Inference on Functionals of Inverse Problems
Andrew Bennett, Nathan Kallus, Xiaojie Mao +3
We consider estimation of parameters defined as linear functionals of solutions to linear inverse problems. Any such parameter admits a doubly robust representation that depends on…
Minimax Instrumental Variable Regression and Convergence Guarantees without Identification or Closedness
Andrew Bennett, Nathan Kallus, Xiaojie Mao +3
In this paper, we study nonparametric estimation of instrumental variable (IV) regressions. Recently, many flexible machine learning methods have been developed for instrumental va…
Provable Safe Reinforcement Learning with Binary Feedback
Andrew Bennett, Dipendra Misra, Nathan Kallus
Safety is a crucial necessity in many applications of reinforcement learning (RL), whether robotic, automotive, or medical. Many existing approaches to safe RL rely on receiving nu…
Inference on Strongly Identified Functionals of Weakly Identified Functions
Andrew Bennett, Nathan Kallus, Xiaojie Mao +3
In a variety of applications, including nonparametric instrumental variable (NPIV) analysis, proximal causal inference under unmeasured confounding, and missing-not-at-random data…
Future-Dependent Value-Based Off-Policy Evaluation in POMDPs
Masatoshi Uehara, Haruka Kiyohara, Andrew Bennett +5
We study off-policy evaluation (OPE) for partially observable MDPs (POMDPs) with general function approximation. Existing methods such as sequential importance sampling estimators…
Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes
Andrew Bennett, Nathan Kallus
In applications of offline reinforcement learning to observational data, such as in healthcare or education, a general concern is that observed actions might be affected by unobser…