Tsunehiko Tanaka

Tsunehiko Tanaka is a researcher specializing in reinforcement learning, sequential decision-making, and structured generation with large language models. He works full-time as a Software Engineer at IBM and part-time as an Adjunct Researcher at Waseda University in Tokyo, where he received his Ph.D. in March 2026 under the supervision of Dr. Edgar Simo-Serra. He is best known for his work on game description generation using LLMs and performance control of reinforcement learning agents, with publications in venues including TMLR, Transactions on Games, and Conference on Games.