publications

2025

1. RLC

   Recursive Reward Aggregation

   Yuting Tang , Yivan Zhang , Johannes Ackermann , and 4 more authors

   RLC, 2025

   Bib

   @article{key,
     author = {Tang, Yuting and Zhang, Yivan and Ackermann, Johannes and Zhang, Yu-jie and Nishimori, Soichiro and Zhang, Yuting and Sugiyama, Masashi},
     journal = {RLC},
     title = {Recursive Reward Aggregation},
     year = {2025}
   }

2. 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},
   }

2024

1. arXiv

   A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees

   Toshinori Kitamura , Tadashi Kozuno , Masahiro Kato , and 6 more authors

   RLC Workshop, 2024

   Bib

   @article{kitamura2024policy,
     title = {A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees},
     author = {Kitamura, Toshinori and Kozuno, Tadashi and Kato, Masahiro and Ichihara, Yuki and Nishimori, Soichiro and Sannai, Akiyoshi and Sonoda, Sho and Kumagai, Wataru and Matsuo, Yutaka},
     journal = {RLC Workshop},
     year = {2024}
   }

2. arXiv

   Leveraging Domain-Unlabeled Data in Offline Reinforcement Learning across Two Domains

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

   arXiv preprint, 2024

   Bib

   @article{nishimori2024leveraging,
     title = {Leveraging Domain-Unlabeled Data in Offline Reinforcement Learning across Two Domains},
     author = {Nishimori, Soichiro and Cai, Xin-Qiang and Ackermann, Johannes and Sugiyama, Masashi},
     journal = {arXiv preprint},
     year = {2024}
   }

3. RLC

   A Batch Sequential Halving Algorithm without Performance Degradation

   Sotetsu Koyamada , Soichiro Nishimori, and Shin Ishii

   RLC, 2024

   Bib

   @article{koyamada2024batch,
     title = {A Batch Sequential Halving Algorithm without Performance Degradation},
     author = {Koyamada, Sotetsu and Nishimori, Soichiro and Ishii, Shin},
     journal = {RLC},
     year = {2024},
   }

4. github

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

   Soichiro Nishimori

   github, 2024

   Bib

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

2023

1. 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},
   }

2. arXiv

   End-to-End Policy Gradient Method for POMDPs and Explainable Agents

   Soichiro Nishimori, Sotetsu Koyamada , and Shin Ishii

   arXiv preprint, 2023

   Bib

   @article{nishimori2023end,
     title = {End-to-End Policy Gradient Method for POMDPs and Explainable Agents},
     author = {Nishimori, Soichiro and Koyamada, Sotetsu and Ishii, Shin},
     journal = {arXiv preprint},
     year = {2023}
   }

2022

1. IEEE

   Mjx: A framework for Mahjong AI research

   Sotetsu Koyamada , Keigo Habara , Nao Goto , and 3 more authors

   In , 2022

   Bib

   @inproceedings{koyamada2022mjx,
     title = {Mjx: A framework for Mahjong AI research},
     author = {Koyamada, Sotetsu and Habara, Keigo and Goto, Nao and Okano, Shinri and Nishimori, Soichiro and Ishii, Shin},
     journal = {2022 IEEE Conference on Games (CoG)},
     pages = {504--507},
     year = {2022},
     organization = {IEEE}
   }