Soichiro Nishimori

@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},
}

@article{nishimori2024jaxcorl,
  title = {JAX-CORL: A single-file repository for offline reinforcement learning},
  author = {Nishimori, Soichiro},
  journal = {github},
  year = {2024},
}

@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},
}

@misc{nishimori2026emergence,
  title = {Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying},
  author = {Nishimori, Soichiro and Parmas, Paavo and Koyamada, Sotetsu and Kozuno, Tadashi and Kitamura, Toshinori and Ishii, Shin and Matsuo, Yutaka},
  year = {2026},
  journal = {ICML},
}

@article{nishimori2026symmetric,
  title = {On Symmetric Losses for Policy Optimization with Noisy Preferences},
  author = {Nishimori, Soichiro and Zhang, Yu-Jie and Lodkaew, Thanawat and Sugiyama, Masashi},
  journal = {Transactions on Machine Learning Research},
  year = {2026},
  url = {https://openreview.net/forum?id=cBWGLmSeao},
}