Kobe University · Graduate School of Economics · 講師

Research keywordsreinforcement learning・policy gradient methods・POMDP agents・game AI・Mahjong AI・bridge bidding AI・parallel game simulators・brain decoding with deep learning

This is a public-data preview. Personalized fit, contact angles, and saved workflows require sign-in.

• Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying2026 · 2026年, International Conference on Machine Learning (ICML)
• A Batch Sequential Halving Algorithm without Performance Degradation.2024 · 2024年, Reinforcement Learning Journal (RLJ), 5, 2218 - 2232
• A Simple, Solid, and Reproducible Baseline for Bridge Bidding AI.2024 · IEEE, 2024年, IEEE Conference on Games (CoG), 1 - 4
• End-to-End Policy Gradient Method for POMDPs and Explainable Agents.2023 · 2023年, arXiv, 2304.09769

• GPUネイティブプランニングアルゴリズムの開発 小山田 創哲 日本学術振興会, 科学研究費助成事業, 若手研究, 神戸大学, 2026年04月01日 - 2029年03月31日2026 · KUID parsed section

• Official profile