Distributional Reinforcement Learning (RL) maintains the entire probability distribution of reward-to-go, i.e. return, providing more learning signals that account for uncertainty associated with policy performance, which may be beneficial trading off exploration and exploitation in general. Previous works distributional RL focused mainly on computing state-action-return distributions, here we ...

A Distributional (Single) Index Model (DIM) is a semiparametric model for distributional regression, that is, estimation of conditional distributions given covariates. The method combination classical single-index models the mean response covariates, and isotonic regression. index parametric, whereas are estimated nonparametrically under stochastic ordering constraint. We show consistency our e...

How does fiscal austerity affect redistributive policies? We document that during episodes, countries tend to increase marginal income tax rates on top earners, but not average earners. then show that, in response an exogenously imposed rule, Italian municipalities local non-linear taxes progressively. They do adjust other policies. College-educated mayors are more likely than less educated imp...

The making of statistical inferences in distributional form is conceptionally complicated because the epistemic 'probabilities' assigned are mixtures of fact and fiction. In this respect they are essentially different from 'physical' or 'frequency-theoretic' probabilities. The distributional form is so attractive and useful, however, that it should be pursued. Our approach is In line with Walds...