Soichiro Nishimori

According to our database, Soichiro Nishimori authored at least 13 papers between 2022 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

Finite-Time Regret Analysis of Retry-Aware Bandits.

Bingkui Tong, Junpei Komiyama, Soichiro Nishimori, Paavo Parmas

CoRR, May, 2026

Mahjax: A GPU-Accelerated Mahjong Simulator for Reinforcement Learning in JAX.

Soichiro Nishimori, Shinri Okano, Keigo Habara, Sotetsu Koyamada, Eason Yu, Masashi Sugiyama

CoRR, May, 2026

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness.

Shinnosuke Ono, Johannes Ackermann, Soichiro Nishimori, Takashi Ishida, Masashi Sugiyama

CoRR, April, 2026

On Symmetric Losses for Policy Optimization with Noisy Preferences.

Soichiro Nishimori, Yu-Jie Zhang, Thanawat Lodkaew, Masashi Sugiyama

Trans. Mach. Learn. Res., 2026

2025

Recursive Reward Aggregation.

Yuting Tang, Yivan Zhang, Johannes Ackermann, Yu-Jie Zhang, Soichiro Nishimori, Masashi Sugiyama

CoRR, July, 2025

On Symmetric Losses for Robust Policy Optimization with Noisy Preferences.

Soichiro Nishimori, Yu-Jie Zhang, Thanawat Lodkaew, Masashi Sugiyama

CoRR, May, 2025

2024

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

Soichiro Nishimori, Xin-Qiang Cai, Johannes Ackermann, Masashi Sugiyama

CoRR, 2024

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

Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato, Yuki Ichihara, Soichiro Nishimori, Akiyoshi Sannai, Sho Sonoda, Wataru Kumagai, Yutaka Matsuo

CoRR, 2024

A Batch Sequential Halving Algorithm without Performance Degradation.

Sotetsu Koyamada, Soichiro Nishimori, Shin Ishii

RLJ, 2024

2023

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

Soichiro Nishimori, Sotetsu Koyamada, Shin Ishii

CoRR, 2023

Pgx: Hardware-accelerated parallel game simulation for reinforcement learning.

Sotetsu Koyamada, Shinri Okano, Soichiro Nishimori, Yu Murata, Keigo Habara, Haruka Kita, Shin Ishii

CoRR, 2023

Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning.

Sotetsu Koyamada, Shinri Okano, Soichiro Nishimori, Yu Murata, Keigo Habara, Haruka Kita, Shin Ishii

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

Mjx: A framework for Mahjong AI research.

Sotetsu Koyamada, Keigo Habara, Nao Goto, Shinri Okano, Soichiro Nishimori, Shin Ishii

Proceedings of the IEEE Conference on Games, CoG 2022, Beijing, 2022