Kokolo Ikeda

Prof. Kokolo Ikeda


Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 December 2020
Verified
Book Chapter
Closed access
PDF file
TOTaishi Oikawa
Taishi Oikawa
CHChu-Hsuan Hsueh
Chu-Hsuan Hsueh
KIKokolo Ikeda
Kokolo Ikeda

13 January 2024 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
Chu-Hsuan HsuehChu-Hsuan Hsueh
Chu-Hsuan Hsueh
KIKokolo Ikeda
Kokolo Ikeda

25 December 2015
Verified
Book Chapter
Closed access
PDF file
KIKokolo Ikeda
Kokolo Ikeda
TSTakanari Shishido
Takanari Shishido
SVSimon Viennot
Simon Viennot



7 November 2025 in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
Verified
Journal Article
Open access
PDF file
KKKyota Kuboki
Kyota Kuboki
TOTatsuyoshi Ogawa
Tatsuyoshi Ogawa
Chu-Hsuan HsuehChu-Hsuan Hsueh
Chu-Hsuan Hsueh
SYShi-jim Yen
Shi-jim Yen
KIKokolo Ikeda
Kokolo Ikeda
In many online competitive games, matchmaking is typically based on ratings systems, such as Elo or Glicko-2. However, these rating systems generally require sufficient matches to achieve accurate estimates, resulting in mismatches with opponents of different skill levels, especially during the early stages. To address this issue, methods for estimating strength from a small number of matches are essential. We use "strength" to refer to a player's overall ability, which can be quantified as a skill level such as a rating tier. In a previous state-of-the-art study, researchers estimated player's skill levels using strength scores learned from human match data. In this paper, we further incorporate policies (i.e., probability distributions of moves) of different skill levels from neural networks trained to imitate human players' gameplay. Namely we combine features from policies and the strength scores to estimate skill levels. We targeted Go and chess, where abundant data is available. Experiments in Go show that our method achieved 80% accuracy in strength estimation when given 10 matches, increasing to 92% when given 20 matches. Compared to the previous state-of-the-art method's 71% and 84%, our approach yields 8% improvements. Similar improvements were observed in chess. Since our method requires no game-specific features, it can be applied to other games or real-world problems.