Toshinori Kitamura

Postdoc, University of Alberta

Joined

September 2021

Names

Toshinori Kitamura (Preferred)

Emails

****@is.naist.jp (Confirmed)

****@sinicx.com (Confirmed)

****@weblab.t.u-tokyo.ac.jp (Confirmed)

****@ualberta.ca (Confirmed)

Personal Links

Homepage

Google Scholar

Career & Education History

Postdoc

University of Alberta (ualberta.ca)

2025 – Present

PhD student

The University of Tokyo (g.ecc.u-tokyo.ac.jp)

2022 – 2025

MS student

Nara Institute of Science and Technology, Japan (naist.jp)

2020 – 2022

Undergrad student

Keio University (keio.jp)

2016 – 2020

Advisors, Relations & Conflicts

Postdoc Advisor

Csaba Szepesvari

2025 – Present

PhD Advisor

Yutaka Matsuo

2022 – 2025

PhD Advisor

Tadashi Kozuno

2022 – 2025

Expertise

Reinforcement Learning

2020 – 2025

Publications

Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying
Soichiro Nishimori, Paavo Parmas, Sotetsu Koyamada, Tadashi Kozuno, Toshinori Kitamura, Shin Ishii, Yutaka Matsuo
- Submitted to ICLR 2026
- Readers: Everyone
A Unified MDP Framework for Solving Robust, Convex, Multi-Discount Constraints, and Beyond
Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno, Kenta Hoshino, Yohei Hosoe, Kazumi Kasaura, Wataru Kumagai, Paavo Parmas, Yutaka Matsuo
- Finding the Frame (RLC 2025)
- Readers: Everyone
Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno, Wataru Kumagai, Kazumi Kasaura, Kenta Hoshino, Yohei Hosoe, Yutaka Matsuo
- https://arxiv.org/pdf/2502.10138
- Readers: Everyone
Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation
Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno, Wataru Kumagai, Kazumi Kasaura, Kenta Hoshino, Yohei Hosoe, Yutaka Matsuo
- NeurIPS 2025 spotlight
- Readers: Everyone
Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form
Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai, Kenta Hoshino, Yohei Hosoe, Kazumi Kasaura, Masashi Hamaya, Paavo Parmas, Yutaka Matsuo
- ICLR 2025 Poster
- Readers: Everyone
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
- RLSW 2024 TalkPoster
- Readers: Everyone
Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice
Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang, Nino Vieillard, Michal Valko, Wenhao Yang, Jincheng Mei, Pierre MENARD, Mohammad Gheshlaghi Azar, Remi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvari, Wataru Kumagai, Yutaka Matsuo
- ICML 2023 Poster
- Readers: Everyone
KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal
Tadashi Kozuno, Wenhao Yang, Nino Vieillard, Toshinori Kitamura, Yunhao Tang, Jincheng Mei, Pierre MENARD, Mohammad Gheshlaghi Azar, Michal Valko, Remi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvari
- 22 Sept 2022 (modified: 13 Feb 2023)
- ICLR 2023 Conference Withdrawn Submission
- Readers: Everyone
ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives
Toshinori Kitamura, Ryo Yonetani
- 12 Oct 2021 (modified: 12 Oct 2025)
- Deep RL Workshop NeurIPS 2021
- Readers: Everyone

Co-Authors

View all 28 co-authors