Dynamic Reinforcement Learning for Optimal Go AI Training: Adaptive Adjustment and Optimization
IEEE Transactions on Consumer Electronics · 2025-02 · 71 (1) · 292-302
DOI: 10.1109/tce.2024.3487141 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Consumer Electronics, 2025-02. Verfasst von Chunjiong Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: Brain Korea 21 (BK21) FOUR Program of the National Research Foundation of Korea funded by the Ministry of Education.
Abstract (Originalsprache)
Go is a popular strategy game today, but due to its large search space and task complexity, ensuring stable AI implementation is challenging. Specifically, Go AI training requires setting a fixed optimal learning rate and schedule, which demands significant TPU and GPU resources. To facilitate Go-AI learning, this research explores adaptive adjustment and optimization techniques for dynamic reinforcement learning neural networks. First, we introduce a dynamic batch size technique that adjusts data volume at each training phase and incorporates dynamic network structure search, considering the number of network layers and residual blocks. Second, we propose a dynamic network topology that automatically modifies the learning rate based on the training batch size at various training phases. Our approach outperforms the baseline in terms of stability and model convergence speed. In 100 games, the Go-AI model achieved a 100% victory rate below the 7th rank and a 98% win rate at the 9th rank and higher.
Förderung
- Brain Korea 21 (BK21) FOUR Program of the National Research Foundation of Korea funded by the Ministry of Education
Zitieren
APA
Zhang, C., Shan, G., Lim, J., & Roh, B. (2025). Dynamic Reinforcement Learning for Optimal Go AI Training: Adaptive Adjustment and Optimization. IEEE Transactions on Consumer Electronics, 71(1), 292-302. https://doi.org/10.1109/tce.2024.3487141
Vancouver
Zhang C, Shan G, Lim J, Roh B. Dynamic Reinforcement Learning for Optimal Go AI Training: Adaptive Adjustment and Optimization. IEEE Transactions on Consumer Electronics. 2025;71(1):292-302. doi:10.1109/tce.2024.3487141
BibTeX
@article{Zhang2025,
author = {Zhang, Chunjiong and Shan, Gaoyang and Lim, Junghyun and Roh, Byeong-Hee},
title = {Dynamic Reinforcement Learning for Optimal Go AI Training: Adaptive Adjustment and Optimization},
journal = {IEEE Transactions on Consumer Electronics},
year = {2025},
volume = {71},
number = {1},
pages = {292--302},
doi = {10.1109/tce.2024.3487141}
}
EUVIMED