Minimax Weight and Q-Function Learning for Off-Policy Evaluation

MinimaxWeightandQ-FunctionLearningforOff-PolicyEvaluationMasatoshiUehara1JiaweiHuang2NanJiang2Abstractfromthecommunity(Liuetal.,2018;Xieetal.,2019),astheyovercomethecurseofhorizonwithrelativelymild...