Externally Valid Policy Choice

We consider the problem of learning personalized treatment policies that are externally valid or generalizable: they perform well in other target populations besides the experimental (or training) population from which data are sampled. We first show that welfare-maximizing policies for the experimental population are robust to shifts in the distribution of outcomes (but not characteristics) between the experimental and target populations. We then develop new methods for learning policies that are robust to shifts in outcomes and characteristics. In doing so, we highlight how treatment effect heterogeneity within the experimental population affects the generalizability of policies. Our methods may be used with experimental or observational data (where treatment is endogenous). Many of our methods can be implemented with linear programming.