Incorrect equation in Lecture 8, n-step a2c? par Ali Bakly, samedi, 27 avril 2024, 17:21 Nombre de réponses : 0 In Lecture 8 it says on the notes to slide 15:Isn't that the n-step reward R? Shouldn't we subtract with V(s_t^{(k)}) to get the Advantage? Permalien