The result is aO(D T) regret bound that holds uniformly for all comparatorsu X.

The result is aO(D T) regret bound that holds uniformly for all comparatorsu X.

We show that this method can solve SDPs in polynomial time in a smoothed analysis setting.

Wethus establish that policy iteration on reward-robust MDPs can have the same time complexityasonregularizedMDPs.

Weprovide asemi-supervised estimation procedure of the optimal rule involving two datasets: a firstlabeled dataset is used to estimate both regression function and conditional variance function while a secondunlabeleddataset is exploited to calibrate the desired rejection rate.