Kohei Ozaki

Kohei Ozaki @smly

Works

Game AI

RiichiEnv: Research Environment for Mahjong AI

A high-performance research environment for Riichi Mahjong AI development. The core game logic is implemented in Rust for fast state transitions and rollouts, with a Python Gym-style API designed for reinforcement learning. Features include compatibility with the Mortal bot via the MJAI protocol, flexible rule configuration (Tenhou/Mahjong Soul presets, 3-player/4-player modes), and an integrated replay viewer for Jupyter notebooks.

smly/RiichiEnv

RiichiLab: Mahjong AI Competition Platform

An open arena for Riichi Mahjong AI where developers can pit their bots against each other 24/7 via WebSocket connections. Participants authenticate with GitHub OAuth, register a bot, and connect using the provided API to play full four-player games in real time.

  • Game server built on RiichiEnv's Rust simulator
  • Bots exchange serialized Observation and Action objects over the WebSocket, sharing the same interface as the local RiichiEnv library
  • OpenSkill-based rating system
  • Detailed game logs with key-event shortcuts, and a replay viewer with permalink support for debugging

riichi.dev

AI Competitions

I have been competing in AI competitions since 2011, spanning over 15 years. I have ranked as high as 4th globally on Kaggle (out of 490K+ users) and earned 23 gold medals.

I actively participate in competitions co-located with top academic conferences such as CVPR, ICCV, and NeurIPS.

Beyond competitions, I have been serving as a Google Developer Expert for Kaggle since 2025.

Satellite Imagery

I have a strong interest in remote sensing technologies and their applications, such as satellite imagery analysis, UAV-based small-object detection, and LiDAR measurements. I am also drawn to geolocalization techniques.

Academic Conferences

Industry

© 2026 Kohei Ozaki · smly