Tsunehiko Tanaka

I am a PhD student at Waseda University, supervised by Edgar Simo-Serra. I am interested in applied reinforcement learning and grammar-aligned code generation with LLMs. I received my Bachelor's degree in Engineering in 2021 and my Master's degree in Engineering in 2023 from Waseda University.

Email  |  Google Scholar  |  X  |  Github  |  Linkedin

profile photo
Publications
Return-Aligned Decision Transformer
Tsunehiko Tanaka, Kenshi Abe, Kaito Ariu, Tetsuro Morimura, Edgar Simo-Serra.
TMLR 2025 J2C Certification
paper | code | DOI
Grammar and Gameplay-aligned RL for Game Description Generation with LLMs
Tsunehiko Tanaka, Edgar Simo-Serra
Conference on Games 2025
paper | code | DOI
Grammar-based Game Description Generation using Large Language Models
Tsunehiko Tanaka, Edgar Simo-Serra
Transactions on Games 2024
paper | code | DOI
DiffG-RL: Leveraging Difference between State and Common Sense
Tsunehiko Tanaka, Daiki Kimura, Michiaki Tatsubori
Findings of EMNLP 2022
paper | code | DOI
Commonsense Knowledge from Scene Graphs for Textual Environments
Tsunehiko Tanaka, Daiki Kimura, Michiaki Tatsubori
AAAI Workshop on Reinforcement Learning in Games 2022
paper | code | DOI
Challenges in Explainability and Knowledge Extraction
Daiki Kimura, Tsunehiko Tanaka, Michiaki Tatsubori, Asim Munawar
Wordplay: When Language Meets Games @ NAACL 2022
paper
LoL-V2T: Large-Scale Esports Video Description Dataset
Tsunehiko Tanaka, Edgar Simo-Serra
CVPRW (CVSports) 2021
project | DOI
Patents
    Tsunehiko Tanaka, Daiki Kimura, Michiaki Tatsubori. Extracting enriched target-oriented common sense from grounded graphs to support next step decision making. U.S. Patent Application 17/812,757, filed 2024.
Review Activities
    IEEE Conference on Games (CoG) 2025
Education
    Waseda University, Tokyo (Apr 2023 - present)
    Ph.D. student in Computer Science and Engineering
    Waseda University, Tokyo (Apr 2021 - Mar 2023)
    Master of Computer Science and Engineering
    Waseda University, Tokyo (Apr 2017 - Mar 2021)
    Bachelor of Computer Science and Engineering
Work Experience
    CyberAgent AI Lab, Tokyo (July 2023 - June 2025)
    Developed a transformer-based offline RL method to control agent performance for modeling game players with diverse skill levels, improving control performance by 54.9%. Implemented a reproducible workflow for transformer-based models using PyTorch and Docker on GCP. Accepted for publication in Transactions on Machine Learning Research (TMLR).
    SAP, Tokyo (Sep 2022 - Mar 2023)
    Developed a sales prototype for stockpile measurements using 3D point cloud processing with Python and OpenCV.
    IBM Research, Tokyo (Aug 2021 - May 2022)
    Developed an RL agent that solves text-based games using external knowledge such as ConceptNet. Achieved a 17% improvement on decision making benchmarks for language models. Accepted to EMNLP and an AAAI Workshop; filed one patent application.
    IDAJ Co., LTD., Yokohama (Feb 2021 - Jul 2021)
    Surveyed accident prediction technologies for driving and developed a technical roadmap for implementation.
    Celsys.Inc., Tokyo (Aug 2019 - Jan 2021)
    Maintained and operated the community website for CLIP STUDIO PAINT using Laravel and Vue.js. Implemented bandit algorithms as benchmarking tools for recommendation engines.
Research Grants and Projects
    Human and AI Understandable Interactive Design Grammars
    (人間とAIが理解できるインタラクション設計文法の構築)
    科学技術振興機構 (JST), Strategic Basic Research Programs, ACT-X, PI. Oct 2023 - Mar 2026.
    project | abstract
    Development of AI Systems that Collaborate with Humans in Designing Digital Content Interactions
    (人間と協力してデジタルコンテンツのインタラクションを設計するAIの構築)
    日本学術振興会 (JSPS), Research Fellowship for Young Scientists, DC2, PI. Apr 2024 - Mar 2026.
    project
    Development of AI Systems that Collaborate with Humans in Designing Digital Content Interactions
    (人間と協力してデジタルコンテンツのインタラクションを設計するAIの構築)
    科学技術振興機構 (JST) Support for Pioneering Research Initiated by the Next Generation, SPRING, PI. Apr 2023 - Mar 2024.
    project
Awards
    Okawa Isao Scholarship for Information and Communication (大川功情報通信学術奨学金) 2024.
    Outstanding Award, Domestic Conference MIRU Young Researcher Program. "倫理審査・人を対象とした実験「AI研究者が配慮すべき倫理とは」" (MIRU若手プログラム優秀賞受賞). 2023. page
    Full Exemption of Japan Student Services Organization Scholarship (日本学生支援機構 第一種奨学金 全額返還免除). 2023.
    Okawa Isao Scholarship for Information and Communication (大川功情報通信学術奨学金). 2022.
    Outstanding Award, Domestic Conference MIRU Young Researcher Program. "研究費の取り方に関するサーベイ" 優秀賞受賞 (MIRU若手プログラム優秀賞受賞). 2022. page
    JGC-SANEYOSHI Scholarship (日揮･実吉奨学会 奨学金). 2022.
    JEES/SoftBank AI Human Resource Development Scholarship (JEES・ソフトバンク AI 人材育成奨学金). 2021.

Design: jonbarron