Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Counterfactual Learning of Stochastic Policies with Continuous Actions: from Models to Offline Evaluation

Houssam Zenati 1, 2 Alberto Bietti 3 Matthieu Martin 1 Eustache Diemert 1 Julien Mairal 2 
2 Thoth - Apprentissage de modèles à partir de données massives
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique - ENS Paris, CNRS - Centre National de la Recherche Scientifique, Inria de Paris
Abstract : Counterfactual reasoning from logged data has become increasingly important for many applications such as web advertising or healthcare. In this paper, we address the problem of learning stochastic policies with continuous actions from the viewpoint of counterfactual risk minimization (CRM). While the CRM framework is appealing and well studied for discrete actions, the continuous action case raises new challenges about modelization, optimization, and offline model selection with real data which turns out to be particularly challenging. Our paper contributes to these three aspects of the CRM estimation pipeline. First, we introduce a modelling strategy based on a joint kernel embedding of contexts and actions, which overcomes the shortcomings of previous discretization approaches. Second, we empirically show that the optimization aspect of counterfactual learning is important, and we demonstrate the benefits of proximal point algorithms and differentiable estimators. Finally, we propose an evaluation protocol for offline policies in real-world logged systems, which is challenging since policies cannot be replayed on test data, and we release a new large-scale dataset along with multiple synthetic, yet realistic, evaluation setups.
Document type :
Preprints, Working Papers, ...
Complete list of metadata
Contributor : Houssam Zenati Connect in order to contact the contributor
Submitted on : Thursday, August 19, 2021 - 6:16:31 PM
Last modification on : Wednesday, June 8, 2022 - 12:50:06 PM


Files produced by the author(s)


  • HAL Id : hal-02883423, version 2



Houssam Zenati, Alberto Bietti, Matthieu Martin, Eustache Diemert, Julien Mairal. Counterfactual Learning of Stochastic Policies with Continuous Actions: from Models to Offline Evaluation. 2021. ⟨hal-02883423v2⟩



Record views


Files downloads