The attempts to make mathematical functions that would model human memory have a long history. In the 18th century, Ebbinghaus studied Exponential Forgetting Curve.

Then spaced repetition and Half Life Regressions have been introduced that were for language learning.

Currently, RL seems more promising in this task. Several works combined both RL and DL. RNNs have been used for the reward prediction. Additionally, it was found that TRPO and TNPG have the best performance, TRPO having a little bit better results than the TNPG.