Concept

How useful is average of sum of outcomes based reward function? (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)

The previous reward functions namely the reward function that uses likelihood depends on the student state which makes them useless if the student is not modeled first. The average of sum of outcomes reward function can eliminate this problem as it doesn't depend on the student state. On the other hand, it would be computationally expensive as the number of exercises would increase. In order to solve this issue, sampling exercises into categories will be helpful.

0

1

Updated 2020-11-02

Tags

Data Science