Precision medicine is an emerging scientific topic for disease treatment and prevention. Given data with individual covariates, treatments and outcomes, researchers can search for the optimal individualized treatment rule (ITR). Existing methods typically require initial estimation of some nuisance models. The double robustness property that can protect from misspecication of either the treatment-free effect or the propensity score has been widely advocated. However, when model misspecification exists, a doubly robust estimate can be consistent but may suffer from downgraded efficiency. Furthermore, most existing methods do not account for the potential problem when the variance of outcome is heterogeneous. Such heteroscedasticity can greatly affect the estimation efficiency of the optimal ITR. In this talk, we will demonstrate that the consequences of misspecified treatment-free effect and heteroscedasticity can be unified as a covariate-treatment dependent variance of residuals. To improve efficiency of the estimated ITR, we propose an Efficient Learning (E-Learning) framework for finding an optimal ITR in the multi-armed treatment setting.