Semi-Parametric Efficient Policy Learning with Continuous Actions

Fiche du document

Date

24 mai 2019

Type de document
Périmètre
Identifiant
Source

arXiv

Collection

arXiv

Organisation

Cornell University


Mots-clés

Economics - Econometrics Computer Science - Machine Learning Mathematics - Statistics Theory Statistics - Machine Learning

Sujets proches En

Pattern Model

Citer ce document

Mert Demirer et al., « Semi-Parametric Efficient Policy Learning with Continuous Actions », arXiv, ID : 10670/1.r2gbh1


Métriques


Partage / Export

Résumé 0

We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value function takes a known parametric form in the treatment, but we are agnostic on how it depends on the observed contexts. We propose a doubly robust off-policy estimate for this setting and show that off-policy optimization based on this estimate is robust to estimation errors of the policy function or the regression model. Our results also apply if the model does not satisfy our semi-parametric form, but rather we measure regret in terms of the best projection of the true value function to this functional space. Our work extends prior approaches of policy optimization from observational data that only considered discrete actions. We provide an experimental evaluation of our method in a synthetic data example motivated by optimal personalized pricing and costly resource allocation.

document thumbnail

Par les mêmes auteurs

Sur les mêmes sujets

Sur les mêmes disciplines

Exporter en