On Instrumental Variable Regression for Deep Offline Policy Evaluation

Yutian Chen, Liyuan Xu, Çaglar Gülçehre, Tom Le Paine, Arthur Gretton, Nando de Freitas, Arnaud Doucet. On Instrumental Variable Regression for Deep Offline Policy Evaluation. Journal of Machine Learning Research, 23, 2022. [doi]

Abstract

Abstract is missing.