DEVELOPING INFRASTRUCTURE FOR REINFORCEMENT LEARNING IN ASSISTMENTSPublic
Downloadable Contentopen in viewer
This project is an extension of the Reinforcement Learning Service (RLS) designed for the ASSISTments learning platform. ASSISTments is an organization that is committed to improving student learning using online software. The RLS is a service that is called whenever a student requests additional instruction or tutoring. The RLS takes different features from the student and the problem then recommends a related video or hint based on those features. Based on if the student successfully answered the problem correctly afterward, the RLS then learns from the results and refines its recommendation algorithm. For our project, we are mainly concerned with what happens when the RLS receives a request and how it communicates with the rest of ASSISTments. We wrote code that will use the information from a student or problem, provide a recommendation with a given model, and will write a detailed log that can be analyzed later.
- This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
- Last modified
- UN Sustainable Development Goals
- Date created
- Resource type
- Rights statement
- In Collection:
Permanent link to this page: https://digital.wpi.edu/show/76537408t