Concept

Comparison between likelihood and average of sum of outcomes based reward functions (research objective) (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)

"DRL agents were first trained using likelihood based reward function and average of sum of correct outcomes based reward function. We evaluated the performance of the trained DRL agents using only likelihood as the the performance metric since likelihood is the expected value of the average of sum of correct outcomes."

0

1

Updated 2020-10-29

Tags

Data Science

Related