Robuta

https://jmlr.org/papers/v23/21-0614.html On Instrumental Variable Regression for Deep Offline Policy Evaluation offline policy evaluation instrumental variable regression deep https://openreview.net/forum?id=_y2G1-i7L8 Asymptotically Exact Error Characterization of Offline Policy Evaluation with Misspecified Linear... We characterize the error of a simple linear OPE method when the function approximation may be completely wrong. As a result, we found a new interpretation and... offline policy evaluation exact error characterization linear