Stimulating student engagement with an AI board game tournament
Project Overview
The document outlines a project-based AI course designed for second-year engineering students, which centers on the development of AI agents for board games. This innovative course combines practical programming skills with gamification and competitive elements to boost student engagement and comprehension of AI concepts. Through a blend of lectures covering programming paradigms, AI algorithms, and project management, students gain hands-on experience that culminates in a tournament where their AI agents compete against one another. The course has demonstrated positive outcomes, including heightened motivation among students and a more profound grasp of AI techniques. However, it also highlights certain challenges, such as the variability in student performance and potential technical issues that may arise during the implementation of projects. Overall, this initiative showcases the effectiveness of generative AI in enhancing educational experiences and fostering a deeper understanding of complex concepts in a collaborative and competitive environment.
Key Applications
AI agent development for a board game tournament
Context: Bachelor's program for second-year engineering students specializing in computer science and electronics
Implementation: Students form groups to build AI agents using network programming and AI methods, culminating in a tournament
Outcomes: Enhanced student motivation, engagement, and understanding of AI concepts; successful completion of working AI agents by most groups
Challenges: Varying performance of student agents, technical issues during competitions, ensuring all students understand AI algorithms
Implementation Barriers
Technical Barrier
Potential technical issues with the tournament system and networking during competitions
Proposed Solutions: Providing students with code for the game server to allow local testing and debugging
Performance Variation
Differences in student performance may affect overall competition outcomes
Proposed Solutions: Designing the evaluation criteria to ensure multiple avenues for achieving good scores, independent of competition results
Project Team
Ken Hasselmann
Researcher
Quentin Lurkin
Researcher
Contact Information
For information about the paper, please contact the authors.
Authors: Ken Hasselmann, Quentin Lurkin
Source Publication: View Original PaperLink opens in a new window
Project Contact: Dr. Jianhua Yang
LLM Model Version: gpt-4o-mini-2024-07-18
Analysis Provider: Openai