Chu-Hsuan Hsueh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chu-Hsuan Hsueh has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
Kokolo Ikeda
6 shared publications- Kokolo Ikeda
Japan Advanced Institute of Science and Technology
6 shared publications - Jr-Chang Chen
National Taipei University
2 shared publications Kyota Kuboki
2 shared publications- SangGyu Nam
Sirindhorn International Institute of Technology, Thammasat University
2 shared publications - Shi-Jim Yen
National Dong Hwa University
2 shared publications
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2418-2427
Event-Based Token Sequences for Audio-Conditioned Music-Game Level Modeling
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 2418-2427
Open AccessEvent-Based Token Sequences for Audio-Conditioned Music-Game Level Modeling
- 1 May 2026
- Published by Springer Nature
- p. 153-165
Making KataGo HumanSL More Human-Like for Amateur-Level Play
- 1 May 2026
- Published by Springer Nature
- p. 153-165
Making KataGo HumanSL More Human-Like for Amateur-Level Play
- Open Access
- 7 November 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Vol. 21 (1) , 81-90
Policies of Multiple Skill Levels for Better Strength Estimation in Games
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.
- 7 November 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment
- Vol. 21 (1) , 81-90
Open AccessPolicies of Multiple Skill Levels for Better Strength Estimation in Games
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.
- 1 November 2025
- Published by SAGE Publications in ICGA Journal: The Journal of the Computer Games Community
- Vol. 47 (4) , 189-192
Advances in Computer Games (ACG 2025) Conference Report
- 1 November 2025
- Published by SAGE Publications in ICGA Journal: The Journal of the Computer Games Community
- Vol. 47 (4) , 189-192
Advances in Computer Games (ACG 2025) Conference Report
- 16 April 2025
- Published by Springer Nature
- p. 116-131
Procedurally Generating Natural-Looking Villages in Minecraft with Ant Colony Optimization Algorithms
- 16 April 2025
- Published by Springer Nature
- p. 116-131
Procedurally Generating Natural-Looking Villages in Minecraft with Ant Colony Optimization Algorithms
- 1 November 2024
- Published by SAGE Publications in ICGA Journal: The Journal of the Computer Games Community
- Vol. 46 (3-4) , 163-166
CLAP_CDC Wins Chinese Dark Chess Tournament
This report provides an overview of the Chinese dark chess tournaments held during the 2024 Computer Olympiad. Six teams from Taiwan, Japan, and France participated in the tournament, with the winner being an Alpha-Zero-based program named CLAP_CDC. In addition, this report comments on two games between CLAP_CDC and other programs.
- 1 November 2024
- Published by SAGE Publications in ICGA Journal: The Journal of the Computer Games Community
- Vol. 46 (3-4) , 163-166
CLAP_CDC Wins Chinese Dark Chess Tournament
This report provides an overview of the Chinese dark chess tournaments held during the 2024 Computer Olympiad. Six teams from Taiwan, Japan, and France participated in the tournament, with the winner being an Alpha-Zero-based program named CLAP_CDC. In addition, this report comments on two games between CLAP_CDC and other programs.
- Open Access
- 11 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 16 (4) , 831-843
More Human-Like Gameplay by Blending Policies From Supervised and Reinforcement Learning
Modeling human players' behaviors in games is a key challenge for making natural computer players, evaluating games, and generating content. To achieve better humancomputer interaction, researchers have tried various methods to create human-like AI. In chess and Go, supervised learning with deep neural networks is known as one of the most effective ways to predict human moves. However, for many other games (e.g., Shogi), it is hard to collect a similar amount of game records, resulting in poor move-matching accuracy of the supervised learning.We propose a method to compensate for the weakness of the supervised learning policy by Blending it with an AlphaZerolike reinforcement learning policy. Experiments on Shogi showed that the Blend method significantly improved the move-matching accuracy over supervised learning models. Experiments on chess and Go with a limited number of game records also showed similar results. The Blend method was effective with both medium and large numbers of games, particularly the medium case. We confirmed the robustness of the Blend model to the parameter and discussed the mechanism why the move-matching accuracy improves. In addition, we showed that the Blend model performed better than existing work that tried to improve the move-matching accuracy.
- 11 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 16 (4) , 831-843
Open AccessMore Human-Like Gameplay by Blending Policies From Supervised and Reinforcement Learning
Modeling human players' behaviors in games is a key challenge for making natural computer players, evaluating games, and generating content. To achieve better humancomputer interaction, researchers have tried various methods to create human-like AI. In chess and Go, supervised learning with deep neural networks is known as one of the most effective ways to predict human moves. However, for many other games (e.g., Shogi), it is hard to collect a similar amount of game records, resulting in poor move-matching accuracy of the supervised learning.We propose a method to compensate for the weakness of the supervised learning policy by Blending it with an AlphaZerolike reinforcement learning policy. Experiments on Shogi showed that the Blend method significantly improved the move-matching accuracy over supervised learning models. Experiments on chess and Go with a limited number of game records also showed similar results. The Blend method was effective with both medium and large numbers of games, particularly the medium case. We confirmed the robustness of the Blend model to the parameter and discussed the mechanism why the move-matching accuracy improves. In addition, we showed that the Blend model performed better than existing work that tried to improve the move-matching accuracy.
- 19 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 16 (4) , 807-820
Using Reinforcement Learning to Generate Levels of Super Mario Bros. With Quality and Diversity
Procedural content generation (PCG) is essential in game development, automating content creation to meet various criteria such as playability, diversity, and quality. This paper leverages reinforcement learning (RL) for PCG to generate Super Mario Bros levels. We formulate the problem into a Markov decision process (MDP), with rewards defined using player enjoyment-based evaluation functions. Challenges in level representation and difficulty assessment are addressed by conditional generative adversarial networks (CGAN) and human-like AI agents that mimic aspects of human input inaccuracies. This ensures that the generated levels are appropriately challenging from human perspectives. Furthermore, we enhance content quality through virtual simulation (VS), which assigns rewards to intermediate actions to address a credit assignment problem (CAP). We also ensure diversity through a diversity-aware greedy policy (DAGP), which chooses not-bad-but-distant actions based on Q-values. These processes ensure the production of diverse and high-quality Super Mario levels. Human subject evaluations revealed that levels generated from our approach exhibit natural connection, appropriate difficulty, non-monotony, and diversity, highlighting the effectiveness of our proposed methods. The novelty of our work lies in the innovative solutions we propose to address challenges encountered in employing PCGRL in Super Mario Bros, contributing to the field of PCG for game development.
- 19 June 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 16 (4) , 807-820
Using Reinforcement Learning to Generate Levels of Super Mario Bros. With Quality and Diversity
Procedural content generation (PCG) is essential in game development, automating content creation to meet various criteria such as playability, diversity, and quality. This paper leverages reinforcement learning (RL) for PCG to generate Super Mario Bros levels. We formulate the problem into a Markov decision process (MDP), with rewards defined using player enjoyment-based evaluation functions. Challenges in level representation and difficulty assessment are addressed by conditional generative adversarial networks (CGAN) and human-like AI agents that mimic aspects of human input inaccuracies. This ensures that the generated levels are appropriately challenging from human perspectives. Furthermore, we enhance content quality through virtual simulation (VS), which assigns rewards to intermediate actions to address a credit assignment problem (CAP). We also ensure diversity through a diversity-aware greedy policy (DAGP), which chooses not-bad-but-distant actions based on Q-values. These processes ensure the production of diverse and high-quality Super Mario levels. Human subject evaluations revealed that levels generated from our approach exhibit natural connection, appropriate difficulty, non-monotony, and diversity, highlighting the effectiveness of our proposed methods. The novelty of our work lies in the innovative solutions we propose to address challenges encountered in employing PCGRL in Super Mario Bros, contributing to the field of PCG for game development.
- 31 May 2024
- Published by Elsevier in Entertainment Computing
- Vol. 52
Proposal and generation of endgame puzzles for an imperfect information game Geister
- 31 May 2024
- Published by Elsevier in Entertainment Computing
- Vol. 52
Proposal and generation of endgame puzzles for an imperfect information game Geister
- 28 March 2024
- Published by Springer Nature
- p. 343-357
Factor Analyses on Positive and Negative Evaluations of Games against Go Programs
- 28 March 2024
- Published by Springer Nature
- p. 343-357
Factor Analyses on Positive and Negative Evaluations of Games against Go Programs