Publications

Forthcoming

• WallZero: Mastering the Game of WallGo with Strategic Analysis
  Hsing-Yu Chen, Jérôme Arjonilla, I-Chen Wu, Ti-Rong Wu
  to appear in Computers and Games (CG)

2026

• Do LLMs Trust the Accuser or the Accusation? Measuring Belief Shifts in Werewolf
  Yu-Yu Yang, Ti-Rong Wu, Hung Guei, Hsing-Yu Chen, I-Chen Wu
  The 2026 Conference on Empirical Methods in Natural Language Processing (EMNLP), Main Conference (Short Paper), October 2026 (Acceptance rate ≈ 15.4%)
• MAPLE: Multi-State Aggregated Policy Evaluation for AlphaZero in Imperfect-Information Games
  Qian-Rong Li, Hung Guei, I-Chen Wu, Ti-Rong Wu
  IEEE Conference on Games (IEEE CoG), September 2026 (Acceptance rate ≈ 37.2%)
• Relevance-Zone Reduction in Game Solving
  Chi-Huang Lin, Ting Han Wei, Chun-Jui Wang, Hung Guei, Chung-Chin Shih, Yun-Jui Tsai, I-Chen Wu, Ti-Rong Wu
  Advances in Computer Games (ACG), volume 16463, pages 3–12, May 2026
• Regret-Guided Search Control for Efficient Learning in AlphaZero [Website] [Code]
  Yun-Jui Tsai, Wei-Yu Chen, Yan-Ru Ju, Yu-Hung Chang, Ti-Rong Wu
  The Fourteenth International Conference on Learning Representations (ICLR), April 2026 (Acceptance rate ≈ 27.4%)
• A Study of Solving Life-and-Death Problems in Go Using Relevance-Zone Based Solvers [Website] [Code]
  Chung-Chin Shih, Ti-Rong Wu, Ting Han Wei, Yu-Shan Hsu, Hung Guei, I-Chen Wu
  IEEE Transactions on Games (ToG), volume 18(1), pages 223–228, March 2026
• Demystifying MuZero Planning: Interpreting the Learned Model [Website] [Code]
  Hung Guei, Yan-Ru Ju, Wei-Yu Chen, Ti-Rong Wu
  IEEE Transactions on Artificial Intelligence (TAI), volume 7(2), pages 1025–1036, February 2026

2025

• Learning Human-Like RL Agents Through Trajectory Optimization with Action Quantization [Website] [Code]
  Jian-Ting Guo*, Yu-Cheng Chen*, Ping-Chun Hsieh, Kuo-Hao Ho, Po-Wei Huang, Ti-Rong Wu, I-Chen Wu
  The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), December 2025 (Acceptance rate ≈ 24.5%)
• Evaluating Game Difficulty in Tetris Block Puzzle
  Chun-Jui Wang, Jian-Ting Guo, Hung Guei, Chung-Chin Shih, Ti-Rong Wu, I-Chen Wu
  The 30th Game Programming Workshop (GPW-25), November 2025
• Bridging Local and Global Knowledge via Transformer in Board Games [Website] [Code]
  Yan-Ru Ju, Tai-Lin Wu, Chung-Chin Shih, Ti-Rong Wu
  The Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI), pages 7446–7454, August 2025 (Acceptance rate ≈ 19.3%)
• Dynamic Sight Range Selection in Multi-Agent Reinforcement Learning
  Weichen Liao, Ti-Rong Wu, I-Chen Wu
  The Twenty-Fourth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1327–1335, May 2025 (Full paper; Acceptance rate ≈ 24.5%)
• Solving 7x7 Killall-Go with Seki Database
  Yun-Jui Tsai, Ting Han Wei, Chi-Huang Lin, Chung-Chin Shih, Hung Guei, I-Chen Wu, Ti-Rong Wu
  Computers and Games (CG), volume 15550, pages 66–76, April 2025
• Strength Estimation and Human-Like Strength Adjustment in Games [Website] [Code]
  Chun Jung Chen*, Chung-Chin Shih*, Ti-Rong Wu
  The Thirteenth International Conference on Learning Representations (ICLR), April 2025 (Acceptance rate ≈ 31.9%)
• OptionZero: Planning with Learned Options [Website] [Code]
  Po-Wei Huang, Pei-Chiun Peng, Hung Guei, Ti-Rong Wu
  The Thirteenth International Conference on Learning Representations (ICLR), April 2025 (Oral ≈ 1.8%; Acceptance rate ≈ 31.9%)
• MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games [Website] [Code]
  Ti-Rong Wu, Hung Guei, Pei-Chiun Peng, Po-Wei Huang, Ting Han Wei, Chung-Chin Shih, Yun-Jui Tsai
  IEEE Transactions on Games (ToG), volume 17(1), pages 125–137, March 2025

2024

• A Local-Pattern Related Look-Up Table
  Chung-Chin Shih, Ting Han Wei, Ti-Rong Wu, I-Chen Wu
  IEEE Transactions on Games (ToG), volume 16(2), pages 282–290, June 2024

2023

• An Empirical Analysis of Gumbel MuZero on Stochastic and Deterministic Einstein Würfelt Nicht!
  Chien-Liang Kuo, Po-Ting Chen, Hung Guei, De-Rong Sung, Chu-Hsuan Hsueh, Ti-Rong Wu, I-Chen Wu
  The 28th International Conference on Technologies and Applications of Artificial Intelligence (TAAI), December 2023
• Game Solving with Online Fine-Tuning [Website] [Code]
  Ti-Rong Wu*, Hung Guei*, Ting Han Wei, Chung-Chin Shih, Jui-Te Chin, I-Chen Wu
  The Thirty-Seventh Conference on Neural Information Processing Systems (NeurIPS), December 2023 (Acceptance rate ≈ 26.1%)

2022

• Gumbel MuZero for the Game of 2048
  Chih-Yu Kao, Hung Guei, Ti-Rong Wu, I-Chen Wu
  The 27th International Conference on Technologies and Applications of Artificial Intelligence (TAAI), December 2022
• Are AlphaZero-like Agents Robust to Adversarial Perturbations? [Code]
  Li-Cheng Lan, Huan Zhang, Ti-Rong Wu, Meng-Yu Tsai, I-Chen Wu, Cho-Jui Hsieh
  The Thirty-Sixth Conference on Neural Information Processing Systems (NeurIPS), November 2022 (Acceptance rate ≈ 25.6%)
• AlphaZero-based Proof Cost Network to Aid Game Solving [Code]
  Ti-Rong Wu*, Chung-Chin Shih, Ting Han Wei*, Meng-Yu Tsai, Wei-Yuan Hsu, I-Chen Wu
  The Tenth International Conference on Learning Representations (ICLR), April 2022 (Acceptance rate ≈ 32.3%)
• A Novel Approach to Solving Goal-Achieving Problems for Board Games [Code]
  Chung-Chin Shih*, Ti-Rong Wu*, Ting Han Wei, I-Chen Wu
  The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI), volume 36, number 9, February 2022 (Acceptance rate ≈ 15.0%)

2021

• Learning to Stop: Dynamic Simulation Monte-Carlo Tree Search
  Li-Cheng Lan, Ti-Rong Wu, I-Chen Wu, Cho-Jui Hsieh
  The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI), volume 35, pages 259–267, February 2021 (Acceptance rate ≈ 21.4%)

2020

• Net2Net Extension for the Alphago Zero Algorithm
  Hsiao-Chung Hsieh*, Ti-Rong Wu*, Ting-Han Wei, I-Chen Wu
  Advances in Computer Games (ACG), volume 12516, pages 131–142, December 2020
• Strength Adjustment and Assessment for MCTS-Based Programs
  An-Jen Liu*, Ti-Rong Wu*, I-Chen Wu*, Hung Guei, Ting-han Wei
  IEEE Computational Intelligence Magazine (CIM), volume 15(3), pages 60–73, August 2020
• Accelerating and Improving AlphaZero Using Population Based Training
  Ti-Rong Wu, Ting-Han Wei, I-Chen Wu
  The Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI), volume 34, pages 1046–1053, February 2020 (Oral ≈ 5.85%; Acceptance rate ≈ 20.6%)

2019

• On Strength Adjustment for MCTS-Based Programs
  I-Chen Wu*, Ti-Rong Wu*, An-Jen Liu*, Hung Guei, Tinghan Wei
  The Thirty-Third AAAI Conference on Artificial Intelligence (AAAI), volume 33, pages 1222–1229, January 2019 (Acceptance rate ≈ 16.2%)

2018

• Multilabeled Value Networks for Computer Go
  Ti-Rong Wu, I-Chen Wu, Guan-Wun Chen, Ting-han Wei, Hung-Chun Wu, Tung-Yi Lai, Li-Cheng Lan
  IEEE Transactions on Games (ToG), volume 10(4), pages 378–389, December 2018

Non-Archival Papers

• LaGO: Latent Action Guidance for Online Reinforcement Learning
  Kuanyen Liu, Renjyun Huang, Ti-Rong Wu
  LM4Plan Workshop at the Forty-Third International Conference on Machine Learning (ICML), 2026
• Interpreting the Learned Model in MuZero Planning
  Hung Guei, Yan-Ru Ju*, Wei-Yu Chen*, Ti-Rong Wu
  The 29th International Conference on Technologies and Applications of Artificial Intelligence (TAAI), December 2024 (Runner-Up Paper Award)
  Extended version: "Demystifying MuZero Planning: Interpreting the Learned Model," published in IEEE TAI (2026).

Patents

• Method for Adjusting the Strength of Turn-Based Game Automatically
  I-Chen Wu, Ti-Rong Wu, An-Jen Liu, Hung Guei, and Tinghan Wei
  USA, 2022