Tadashi Kozuno

Identifiers

• name variant Tadashi Kozuno 0.60 · backfill

Papers (6)

1. Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying cs.LG · 2026 · author #4
2. The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback cs.LG · 2026 · author #3
3. Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier cs.LG · 2026 · author #3
4. Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form cs.LG · 2024 · author #2
5. Gap-Increasing Policy Evaluation for Efficient and Noise-Tolerant Reinforcement Learning cs.LG · 2019 · author #1
6. Unifying Value Iteration, Advantage Learning, and Dynamic Policy Programming stat.ML · 2017 · author #1

Mentions

• 2606.00151 #4 · arxiv_oai · confidence 0.70 Tadashi Kozuno

Frequent Coauthors

• Kenji Doya 2 shared papers
• Michal Valko 2 shared papers
• Paavo Parmas 2 shared papers
• Toshinori Kitamura 2 shared papers
• Vianney Perchet 2 shared papers
• Yutaka Matsuo 2 shared papers
• C\^ome Fiegel 1 shared papers
• Come Fiegel 1 shared papers
• Dongqi Han 1 shared papers
• Eiji Uchibe 1 shared papers
• Kazumi Kasaura 1 shared papers
• Kenta Hoshino 1 shared papers
• Masashi Hamaya 1 shared papers
• Pierre M\'enard 1 shared papers
• Pierre Menard 1 shared papers
• Shin Ishii 1 shared papers
• Soichiro Nishimori 1 shared papers
• Sotetsu Koyamada 1 shared papers
• Wataru Kumagai 1 shared papers
• Yohei Hosoe 1 shared papers