SSP-MMC-FSRS is an extended verson of SSP-MMC, which is an algorithm for minimizing the memorization cost in spaced repetiton. The core hypothesis of SSP-MMC is the learner will memorize a card forever when the stability exceeds a certain threshold. With this hypothesis, and the memory state-transition function (provided by FSRS), we can formulate the problem as a special case of the Markov Decision Process (MDP), i.e., a stochastic shortest path problem.
open-spaced-repetition/SSP-MMC-FSRS
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.