Kazuki Ota

I am a Ph.D. student in Engineering at The University of Tokyo, advised by Takayuki Osa and Tatsuya Harada. I am also a part-time researcher at RIKEN AIP.

I aim to create machines that bring novel insights to humanity. To this end, I study reinforcement-learning systems that discover strong strategies and valuable ideas given only the rules of a domain.

Email / LinkedIn / X (Twitter) / Google Scholar / GitHub

Portrait of Kazuki Ota

Research

I study reinforcement-learning systems that can search, test, and organize ideas beyond direct human supervision. My recent work explores this direction in two settings: stable and efficient self-play for discovering strong strategies in two-player games, and self-supervised theorem discovery from axioms alone in formal mathematical environments.

Reinforcement Learning Self-Play Search and Planning AI for Mathematics Theorem Discovery

Research desk with notebook, laptop, and mathematical sketches

Selected Publications

Awards

Background

Education

  • Ph.D. in Engineering, The University of Tokyo, 2024-present
  • M.Sc. in Computer Science, The University of Tokyo, 2022-2024
  • B.Sc. in Information Science, The University of Tokyo, 2018-2022

Experience

  • Part-Time Researcher, RIKEN AIP, 2024-present
  • Part-Time, Preferred Networks, Inc., 2024-2025
  • Intern, Preferred Networks, Inc., 2022