Adaptive AI Systems in Air Hockey: Reinforcement Learning Implementation with Self-Play for Optimization
OnBoard Knowledge Journal · 2025
DOI: 10.70554/objk2025.v01n02.04 ↗Kurz gefasst
Fachartikel in der Zeitschrift OnBoard Knowledge Journal, 2025. Verfasst von Flavio Andrés Arregoces Mercado und 4 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
This paper presents an adaptive AI system for educational Air Hockey that combines Proximal Policy Optimization (PPO) with self-play mechanisms to create intelligent agents capable of strategic adaptation while promoting climate change awareness. The proposed approach integrates three main contributions: a hybrid PPO-Self-Play architecture with behavioral correction systems to prevent suboptimal patterns, a 21-dimensional observation system that includes normalized positions, velocities, and trajectory prediction, and an adaptive self-play mechanism that trains agents against previous versions with varying difficulty levels. The system implements a multi-objective reward function and curriculum learning to guide agents toward competitive and efficient behaviors. The educational game "HOCKEY IS MELTING DOWN" uses polar ice melting as a metaphor to raise environmental awareness through interactive gameplay. Experimental results demonstrate substantial improvements over baseline methods, with the final model achieving an 81% win rate and significantly outperforming random agents, heuristic AI, and simple DQN implementations. Specialized evaluation metrics and usability testing with human participants confirm the system’s effectiveness as both a competitive gaming AI and an engaging educational tool for climate change awareness.
Zitieren
APA
Mercado, F. A. A., Franco, C. D. G., Gonzáles, B. V. M., Barreneche, J. L. S., & Ye, Y. Z. (2025). Adaptive AI Systems in Air Hockey: Reinforcement Learning Implementation with Self-Play for Optimization. OnBoard Knowledge Journal. https://doi.org/10.70554/objk2025.v01n02.04
Vancouver
Mercado FAA, Franco CDG, Gonzáles BVM, Barreneche JLS, Ye YZ. Adaptive AI Systems in Air Hockey: Reinforcement Learning Implementation with Self-Play for Optimization. OnBoard Knowledge Journal. 2025. doi:10.70554/objk2025.v01n02.04
BibTeX
@article{Mercado2025,
author = {Mercado, Flavio Andrés Arregoces and Franco, Cristian David Gonzáles and Gonzáles, Bella Valentina Mejía and Barreneche, Jorge Luis Sanchez and Ye, Yovany Zhu},
title = {Adaptive AI Systems in Air Hockey: Reinforcement Learning Implementation with Self-Play for Optimization},
journal = {OnBoard Knowledge Journal},
year = {2025},
doi = {10.70554/objk2025.v01n02.04}
}
EUVIMED