How useful is LSTM for reward prediction? (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)
Another method to eliminate the dependence of reward function on the student state was using LSTMs for predicting the probability of student being correct. It was surprising that on the data that was generated Supermemo performed a lot better than the LSTM that was trained on the interaction data that was generated by other two models. This supports the idea that the better the interaction data better the LSTM performance. Additionally , LSTMs showed better performance that the average of sum of outcomes reward function.
0
1
Tags
Data Science
Related
Summary of findings (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)
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)
How useful is LSTM for reward prediction? (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)
Limitations (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)
Sustainability and Ethics (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)
Future Work (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)