A Principled Path to Fitted Distributional Evaluation
atari gamesconvergence analysisdistributional off-policy evaluationexpectation-based reinforcement learningfitted distributional evaluationfitted q-evaluationguiding principleslinear quadratic regulatorsnon-tabular environmentsreinforcement learningreturn distributionsimulationssuperior performancetheoretical justificationtheoretically grounded methodsunified framework
In reinforcement learning, distributional off-policy evaluation (OPE) focuses on estimating the return distribution of a target policy using offline data collected under a different policy. This work focuses on extending the widely used fitted Q-evaluation