High sample complexity has long been a challenge for RL.

Four approaches are discussed: Variational Bounds of Mutual Information, Density Matching, ProbabilisticClassifier,andDensity-RatioFitting. Proposition3(IJS and its neural estimation, restating Jensen-Shannon bound with f-GAN objective [22]). We adopt the "concatenate critic" design [20, 22, 23] for our neural network parametrized function. NotethatProbabilistic Classifier method applies sigmoid function to the outputs to ensure probabilistic outputs. To proceed, it suffices if we could provide an upper bound forPrS(|lS(θk)| ε/2).

Sinceitsinception, theneuralestimation ofmutualinformation (MI)hasdemonstrated the empirical success of modeling expected dependency between highdimensional random variables.

" representationand "F" means F-measure.

Our result suggests that finding a simple structured relation and learning a model with extrapolation capability are two sides of the same coin.