Soichiro Nishimori

I am Soichiro Nishimori, a PhD student at Sugiyama-Yokoya-Ishida lab supervised by Prof. Sugiyama. Also, I am working as a research part-timer in Geoinformatics Team at RIKEN AIP. I am into Reinforcement Learning (RL): (1) JAX based RL for full utilization of the GPU power, (2) Game AI research as a testbed for real world application, (3) Statistical RL.

news

May 09, 2025	2 papers are accepted to RLC 2025.
Apr 01, 2024	I started PhD journey at UTokyo!
Apr 01, 2024	I started to work at RIKEN AIP as research part-timer.
Oct 25, 2023	I was selected as JSPS DC1 Fellow.

latest posts

Oct 11, 2025	シドニー大学滞在記 (準備編)
Jul 11, 2024	Offline RLもJAX!!:JAX-CORLの紹介及び開発過程
Apr 09, 2024	個人ページ作りました．

selected publications

NIPS

Pgx: Hardware-accelerated parallel game simulators for reinforcement learning

Sotetsu Koyamada , Shinri Okano , Soichiro Nishimori, and 4 more authors

NeurIPS, 2023

Bib

@article{koyamada2024pgx,
  title = {Pgx: Hardware-accelerated parallel game simulators for reinforcement learning},
  author = {Koyamada, Sotetsu and Okano, Shinri and Nishimori, Soichiro and Murata, Yu and Habara, Keigo and Kita, Haruka and Ishii, Shin},
  journal = {NeurIPS},
  volume = {36},
  year = {2023},
}

github

JAX-CORL: A single-file repository for offline reinforcement learning

Soichiro Nishimori

github, 2024

Bib

RLC

Offline Reinforcement Learning with Domain-Unlabeled Data

Soichiro Nishimori, Xin-Qiang Cai , Johannes Ackermann , and 1 more author

RLC, 2025

Bib

@article{nishimori2025offline,
  title = {Offline Reinforcement Learning with Domain-Unlabeled Data},
  author = {Nishimori, Soichiro and Cai, Xin-Qiang and Ackermann, Johannes and Sugiyama, Masashi},
  journal = {RLC},
  year = {2025},
}