This learning approach trains an agent by letting it interact with an environment and observe the consequences of its actions. After each action, the agent receives feedback in the form of rewards or penalties, then adjusts its behavior to improve future outcomes. The objective is to choose actions that maximize long-term reward, not just the next immediate payoff. This is especially useful for tasks where decisions affect later results, such as game playing, robot control, or scheduling.

Learning from Rewards and Penalties

1. Reinforcement Learning
2. Intelligent Tutoring Systems

San Diego State University

1. History
2. Related Theory
3. Related Work

Background and Related Work (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)

1. Models of Human Memory
2. Spaced Repetition
3. Leitner System
4. Supermemo System
5. Intelligent Tutoring System
6. Relation between Tutoring Systems and Student Learning
7. Reinforcement Learning
8. Trust Region Policy Optimization
9. Truncated Natural Policy Gradient
10. Recurrent Neural Networks

Related Theory (Using deep reinforcement learning for personalizing review sessions on e-learning platforms with spaced repetition)

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. 
  

Learn Before

Related

Learn After