Grading Complex Interactive Coding Programs with Reinforcement Learning
中文摘要
AI trains game-playing agents for various retro games like Atari and DotA. This research advances machine learning for game AI.
English Summary
This research applies reinforcement learning techniques, previously used for game-playing AI, to evaluate and grade complex, interactive coding programs.
[Summary] tl;dr: A tremendous amount of effort has been poured into training AI algorithms to competitively play games that computers have traditionally had trouble with, such as the retro games published by Atari, Go, DotA, and StarCraft II. The practical machine learning knowledge accumulated in developing these algorithms has paved the way for people to now routinely train game-playing AI agents for many games. Following this line of work, we focus on a specific category of games – those developed by students as part of a programming assignment. Can the same algorithms that master Atari games help us grade these game assignments? In our recent NeurIPS 2021 paper, we illustrate the challenges in treating interactive coding assignment grading as game playing and introduce the Play to Grade Challenge. Introduction Massive Online Coding Education has reached striking success over the past decade. Fast internet speed, improved UI design, code editors that are embedded in a browser window allow educational platforms such as Code.org to build a diverse set of courses tailored towards students of different coding experiences and interest levels (for example, Code.org offers “Star War-th…