Toshinori Kitamura
Scholar

Toshinori Kitamura

Google Scholar ID: -gi3cKgAAAAJ
The University of Tokyo
Reinforcement Learning
Citations & Impact
All-time
Citations
35
 
H-index
4
 
i10-index
1
 
Publications
12
 
Co-authors
29
list available
Resume (English only)
Academic Achievements
  • 2025, ICLR paper: 'Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form'
  • 2025, Finding the Frame Workshop at RLC 2025: 'A Unified MDP Framework for Solving Robust, Convex, Multi-Discount Constraints, and Beyond'
  • 2025, NeurIPS Spotlight: 'Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation'
  • 2024, arXiv preprint: 'A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees'
  • 2023, ICML paper: 'Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice'
  • 2021, ACML papers: 'Cautious Actor-Critic' and 'Geometric Value Iteration: Dynamic Error-Aware KL Regularization for Reinforcement Learning'
  • 2021, arXiv preprint: 'ShinRL: A Library for Evaluating RL Algorithms from Theoretical and Practical Perspectives'
  • Multiple arXiv preprints and domestic conference papers in Japan
Education
  • Postdoctoral Researcher, University of Alberta, starting Sep 2025
  • Postdoctoral Researcher, The University of Tokyo, 2025–Sep 2025
  • Ph.D. in Engineering, The University of Tokyo, 2022–2025; supervised by Dr. Tadashi Kozuno and Prof. Yutaka Matsuo
  • M.S. in Science and Technology, Nara Institute of Science and Technology, 2020–2022; supervised by Prof. Takamitsu Matsubara
  • Exchange Student, University of California Davis, 2018
  • B.E. in Science and Technology, Keio University, 2016–2020