weagree
e0e2b58d64fb37a2527329a5ce093d80-AuthorFeedback.pdf
One starting point in this direction would be to2 consider the simplified setting of contextual bandits with linear reward functions.
fdff71fcab656abfbefaabecab1a7f6d-AuthorFeedback.pdf
Theother summaries based on1Dpersistence hadrunning15 times similar to MP-I.Size of feature space It is correct that we worked with 10x10 and 50x5016 images. For example, inR3, one would sweep the 3D space31 with planes thatallintersect onagivenline. We also thank R1 for the writing comments and reference works. We answer37 their questions here.DTM: we didn't study stability w.r.t. the DTM parameters but this is a very38 interestingquestiontolookat.