This interesting new paper tries to improve on model-based SRS scheduling algorithms by adding *planning*—that is, given a student's time constraints, find an optimal sequence. Surprisingly, doesn't do significantly better than typical "greedy" approaches. arxiv.org/pdf/2102.04174
Conversation
Replying to
The intelligent tutoring system literature has many systems which try to do this (including inferring the dependency relations). They frame it as a general learning optimization problem, rather than a variant of SRS—a more general lens. Very high param count though…