Hung Guei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Hung Guei has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Ti-Rong Wu
Academia Sinica
5 shared publications - Chung-Chin Shih
Institute of Information Science, Academia Sinica, Taipei, Taiwan
4 shared publications - I-Chen Wu
National yang Ming Chiao Tung University
4 shared publications - Ting Han Wei
University of Alberta
3 shared publications - Yun-Jui Tsai
National yang Ming Chiao Tung University
3 shared publications - Chi-Huang Lin
National yang Ming Chiao Tung University
2 shared publications
Latest Publications
- 1 May 2026
- Published by Springer Nature
- p. 3-12
Relevance-Zone Reduction in Game Solving
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 18 (1) , 223-228
A Study of Solving Life-and-Death Problems in Go Using Relevance-Zone-Based Solvers
This paper analyzes the behavior of solving Life-and-Death (L&D) problems in the game of Go using current state-of-the-art computer Go solvers with two techniques: the Relevance-Zone Based Search (RZS) and the relevance-zone pattern table. We examined the solutions derived by relevance-zone based solvers on seven L&D problems from the renowned book “Life and Death Dictionary” written by Cho Chikun, a Go grandmaster, and found several interesting results. First, for each problem, the solvers identify a relevance-zone that highlights the critical areas for solving. Second, the solvers discover a series of patterns, including some that are rare. Finally, the solvers even find different answers compared to the given solutions for two problems. We also identified two issues with the solver: (a) it misjudges values of rare patterns, and (b) it tends to prioritize living directly rather than maximizing territory, which differs from the behavior of human Go players. We suggest possible approaches to address these issues in future work.
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 18 (1) , 223-228
A Study of Solving Life-and-Death Problems in Go Using Relevance-Zone-Based Solvers
This paper analyzes the behavior of solving Life-and-Death (L&D) problems in the game of Go using current state-of-the-art computer Go solvers with two techniques: the Relevance-Zone Based Search (RZS) and the relevance-zone pattern table. We examined the solutions derived by relevance-zone based solvers on seven L&D problems from the renowned book “Life and Death Dictionary” written by Cho Chikun, a Go grandmaster, and found several interesting results. First, for each problem, the solvers identify a relevance-zone that highlights the critical areas for solving. Second, the solvers discover a series of patterns, including some that are rare. Finally, the solvers even find different answers compared to the given solutions for two problems. We also identified two issues with the solver: (a) it misjudges values of rare patterns, and (b) it tends to prioritize living directly rather than maximizing territory, which differs from the behavior of human Go players. We suggest possible approaches to address these issues in future work.
- 22 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (2) , 1025-1036
Demystifying MuZero Planning: Interpreting the Learned Model
MuZero has achieved superhuman performance in various games by using a dynamics network to predict the environment dynamics for planning, without relying on simulators. However, the latent states learned by the dynamics network make its planning process opaque. This paper aims to demystify MuZero’s model by interpreting the learned latent states. We incorporate observation reconstruction and state consistency into MuZero training and conduct an in-depth analysis to evaluate latent states across two board games: 9x9 Go and Gomoku, and three Atari games: Breakout, Ms. Pacman, and Pong. Our findings reveal that while the dynamics network becomes less accurate over longer simulations, MuZero still performs effectively by using planning to correct errors. Our experiments also show that the dynamics network learns better latent states in board games than in Atari games. These insights contribute to a better understanding of MuZero and offer directions for future research to improve the performance, robustness, and interpretability of the MuZero algorithm. The code and data are available at https://rlg.iis.sinica.edu.tw/papers/demystifying-muzero-planning.
- 22 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (2) , 1025-1036
Demystifying MuZero Planning: Interpreting the Learned Model
MuZero has achieved superhuman performance in various games by using a dynamics network to predict the environment dynamics for planning, without relying on simulators. However, the latent states learned by the dynamics network make its planning process opaque. This paper aims to demystify MuZero’s model by interpreting the learned latent states. We incorporate observation reconstruction and state consistency into MuZero training and conduct an in-depth analysis to evaluate latent states across two board games: 9x9 Go and Gomoku, and three Atari games: Breakout, Ms. Pacman, and Pong. Our findings reveal that while the dynamics network becomes less accurate over longer simulations, MuZero still performs effectively by using planning to correct errors. Our experiments also show that the dynamics network learns better latent states in board games than in Atari games. These insights contribute to a better understanding of MuZero and offer directions for future research to improve the performance, robustness, and interpretability of the MuZero algorithm. The code and data are available at https://rlg.iis.sinica.edu.tw/papers/demystifying-muzero-planning.
- 1 April 2025
- Published by Springer Nature
- p. 66-76
Solving 7x7 Killall-Go with Seki Database
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 17 (1) , 125-137
MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games
This paper presents MiniZero , a zero-knowledge learning framework that supports four state-of-the-art algorithms, including AlphaZero, MuZero, Gumbel AlphaZero, and Gumbel MuZero. While these algorithms have demonstrated super-human performance in many games, it remains unclear which among them is most suitable or efficient for specific tasks. Through MiniZero , we systematically evaluate the performance of each algorithm in the two board games, 9x9 Go and 8x8 Othello, as well as 57 Atari games. For the two board games, using more simulations generally results in higher performance. However, the choice between AlphaZero and MuZero may differ based on game properties. For Atari games, both MuZero and Gumbel MuZero are worth considering. Since each game has unique characteristics, different algorithms and simulations yield varying results. In addition, we introduce an approach, called progressive simulation, which progressively increases the simulation budget during training to allocate computation more efficiently. Our empirical results demonstrate that progressive simulation achieves significantly superior performance in the two board games. By making our framework and trained models publicly available, this paper contributes a benchmark for future research on zero-knowledge learning algorithms, assisting researchers in algorithm selection and comparison against these zero-knowledge learning baselines. Our code and data are available at https://rlg.iis.sinica.edu.tw/papers/minizero .
- 30 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 17 (1) , 125-137
MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games
This paper presents MiniZero , a zero-knowledge learning framework that supports four state-of-the-art algorithms, including AlphaZero, MuZero, Gumbel AlphaZero, and Gumbel MuZero. While these algorithms have demonstrated super-human performance in many games, it remains unclear which among them is most suitable or efficient for specific tasks. Through MiniZero , we systematically evaluate the performance of each algorithm in the two board games, 9x9 Go and 8x8 Othello, as well as 57 Atari games. For the two board games, using more simulations generally results in higher performance. However, the choice between AlphaZero and MuZero may differ based on game properties. For Atari games, both MuZero and Gumbel MuZero are worth considering. Since each game has unique characteristics, different algorithms and simulations yield varying results. In addition, we introduce an approach, called progressive simulation, which progressively increases the simulation budget during training to allocate computation more efficiently. Our empirical results demonstrate that progressive simulation achieves significantly superior performance in the two board games. By making our framework and trained models publicly available, this paper contributes a benchmark for future research on zero-knowledge learning algorithms, assisting researchers in algorithm selection and comparison against these zero-knowledge learning baselines. Our code and data are available at https://rlg.iis.sinica.edu.tw/papers/minizero .
- 3 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 14 (3) , 478-487
Optimistic Temporal Difference Learning for 2048
Temporal difference (TD) learning and its variants, such as multistage TD learning and temporal coherence (TC) learning, have been successfully applied to 2048 . These methods rely on the stochasticity of the environment of 2048 for exploration. In this article, we propose to employ optimistic initialization (OI) to encourage exploration for 2048 , and empirically show that the learning quality is significantly improved. This approach optimistically initializes the feature weights to very large values. Since weights tend to be reduced once the states are visited, agents tend to explore those states which are unvisited or visited few times. Our experiments show that both TD and TC learning with OI significantly improve the performance. As a result, the network size required to achieve the same performance is significantly reduced. With additional tunings such as expectimax search, multistage learning, and tile-downgrading technique, our design achieves the state-of-the-art performance, namely an average score of 625 377 and a rate of 72% reaching 32 768-tiles. In addition, for sufficiently large tests, 65 536-tiles are reached at a rate of 0.02%.
- 3 September 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Games
- Vol. 14 (3) , 478-487
Optimistic Temporal Difference Learning for 2048
Temporal difference (TD) learning and its variants, such as multistage TD learning and temporal coherence (TC) learning, have been successfully applied to 2048 . These methods rely on the stochasticity of the environment of 2048 for exploration. In this article, we propose to employ optimistic initialization (OI) to encourage exploration for 2048 , and empirically show that the learning quality is significantly improved. This approach optimistically initializes the feature weights to very large values. Since weights tend to be reduced once the states are visited, agents tend to explore those states which are unvisited or visited few times. Our experiments show that both TD and TC learning with OI significantly improve the performance. As a result, the network size required to achieve the same performance is significantly reduced. With additional tunings such as expectimax search, multistage learning, and tile-downgrading technique, our design achieves the state-of-the-art performance, namely an average score of 625 377 and a rate of 72% reaching 32 768-tiles. In addition, for sufficiently large tests, 65 536-tiles are reached at a rate of 0.02%.