A two-stage Q-learning algorithm jointly chooses treatments and which covariates to collect, maximizing expected outcome minus assessment and treatment costs.
This motivates the definition of Y 1t∗ j1 = Y − C 2t(A2) + (¯S2, A1)⊤ ¯α∗{I(S⊤ ¯jf 2 α∗ j1A1jf 2 > 0) − A2} − C 2c(jf
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ME 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Balancing utility and cost in dynamic treatment regimes
A two-stage Q-learning algorithm jointly chooses treatments and which covariates to collect, maximizing expected outcome minus assessment and treatment costs.