Offline Multi-Action Policy Learning: Generalization and Optimization 1: Cross-Fitted AIPW Policy Learning Has Regret O_p(κ(Π)√(V*/n)) Even with Slowly Converging Nuisance EstimatesResearch Paper
Many decisions are made by assigning one of several actions to an individual on the basis of observed features: which of drugs to prescribe, which of several promotions to show, which job-training programme to offer. Experimentation is often costly or unethical, while historical records of past assignments and their outcomes are plentiful. Offline policy…