Author name: Xiang Li, Nan Jiang

arXiv:2605.06474v2 Announce Type: replace-cross
Abstract: We present a novel theoretical framework, Q-MMR, for off-policy evaluation in finite-horizon MDPs. Q-MMR learns a set of scalar weights, one for each data point, such that the reweighted reward…

arXiv:2605.06474v1 Announce Type: cross
Abstract: We present a novel theoretical framework, Q-MMR, for off-policy evaluation in finite-horizon MDPs. Q-MMR learns a set of scalar weights, one for each data point, such that the reweighted rewards approx…