Kyushu University Academic Staff Educational and Research Activities Database
Researcher information (To researchers) Need Help? How to update
Kazuki Yoshizoe Last modified date:2023.05.29

Graduate School
Undergraduate School
Other Organization

E-Mail *Since the e-mail address is not displayed in Internet Explorer, please use another web browser:Google Chrome, safari.
 Reseacher Profiling Tool Kyushu University Pure
Academic Degree
Ph.D. (Computer Science)
Country of degree conferring institution (Overseas)
Field of Specialization
Search Algorithms, Parallel Algorithms, Parallel Computing, Game AI, Computer Go
ORCID(Open Researcher and Contributor ID)
Total Priod of education and research career in the foreign country
Research Interests
  • Solving real-world problems including, but not limited to, chemistry and material science using machine learning and graph search.
    keyword : Graph Search, Machine Learning, Chemical Compounds, Material Science
  • Large-Scale Parallelization of Graph Search Algorithms
    keyword : Graph Search Algorithms, Distributed Memory Parallelization
Academic Activities
1. Xiufeng Yang, Tanuj Kr Aasawat, Kazuki Yoshizoe, Practical Massively Parallel Monte-Carlo Tree Search Applied to Molecular Design., The Ninth International Conference on Learning Representations (ICLR2021), 2021.05.
2. Kazuki Yoshizoe, Akihiro Kishimoto, Tomoyuki Kaneko, Haruhiro Yoshimoto, Yutaka Ishikawa, Scalable Distributed Monte Carlo Tree Search, Proceedings of The Fourth Annual Symposium on Combinatorial Search (SoCS2011), 4, 180-187, 2011.07.
3. Kazuki Yoshizoe, Akihiro Kishimoto, Martin Mueller, Lambda Depth-first Proof Number Search and its Application to Go, 20TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-2007), 2404-2409, 2007.01, Thomsen's lambda search and Nagai's depth-first proof-number (DFPN) search are two powerful but very different AND/OR tree search algorithms. Lambda Depth-First Proof Number search (LDFPN) is a novel algorithm that combines ideas from both algorithms. lambda search can dramatically reduce a search space by finding different levels of threat sequences. DFPN employs the notion of proof and disproof numbers to expand nodes expected to be easiest to prove or disprove. The method was shown to be effective for many games. Integrating lambda order with proof and disproof numbers enables LDFPN to select moves more effectively, while preserving the efficiency of DFPN. LDFPN has been implemented for capturing problems in Go and is shown to be more efficient than DFPN and more robust than an algorithm based on classical lambda search..