Rui Song (North Carolina State University)
Title:听Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process.
础产蝉迟谤补肠迟:听In this talk, we consider constructing a confidence interval for a target policy鈥檚 value offline based on pre-collected observational data in infinite horizon settings. Most of the existing works assume no unmeasured variables exist that confound the observed actions. This assumption, however, is likely to be violated in real applications such as healthcare and technological industries. We show that with some auxiliary variables that mediate the effect of actions on the system dynamics, the target policy鈥檚 value is identifiable in a confounded Markov decision process. Based on this result, we develop an efficient off-policy value estimator that is robust to potential model misspecification and provides rigorous uncertainty quantification.
听
听
Zoom:
Meeting ID: 834 3668 6293
Passcode: 12345