Tadashi Kozuno

16 papers · 2019–2025 · 5 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+6 more ↓

🗺️ Taxonomy Completionist (31) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird

🧬 Topic Evolution 🗃️ Keyword Collector (81) 📈 Trend Setter 💎 Century Club · Bronze 🔥 Unstoppable · Bronze ⚡ Prolific Year · Productive

Venues

ICML (6) NeurIPS (6) ICLR (2) AISTATS (1) JMLR (1)

Top co-authors

Michal Valko (8) Rémi Munos (8) Pierre Menard (5) Yunhao Tang (4) Yutaka Matsuo (4) Côme Fiegel (3) Mark Rowland (3) Vianney Perchet (3) Toshinori Kitamura (2) Olivier Pietquin (2)

Research topics

Reinforcement Learning (14) Machine Learning (13) Methods (12) Learning Types · Machine Learning (9) Optimization & Theory (8) Artificial Intelligence (6) Core AI (6) Applications (5) Mathematics & Optimization (4) Optimization (4) Deep Learning (1) Bayesian & Probabilistic (1) Learning Types · Deep Learning (1) Mathematics (1)

Keywords

reinforcement learning (8) value iteration (3) policy gradient (3) policy optimization (2) mirror descent (2) deep reinforcement learning (2) nash equilibrium (2) zero-sum game (2) off-policy learning (2) multi-step learning (2) imperfect information game (2) online mirror descent (2) theoretical analysis (1) policy learning (1) minimax optimality (1) sample complexity (1) variational inference (1) kl divergence (1) online learning (1) regret minimization (1)

Papers

Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form ICLR 2025 The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback ICML 2025 Local and Adaptive Mirror Descents in Extensive-Form Games NeurIPS 2024 Adapting to game trees in zero-sum imperfect information games ICML 2023 DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm ICML 2023 Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice ICML 2023 Confident Approximate Policy Iteration for Efficient Local Planning in q^π-realizable MDPs NeurIPS 2022 Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences JMLR 2022 Variational oracle guiding for reinforcement learning ICLR 2022 Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning NeurIPS 2021 Learning in two-player zero-sum partially observable Markov games with perfect recall NeurIPS 2021 Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning ICML 2021 Revisiting Peng’s Q($λ$) for Modern Reinforcement Learning ICML 2021 Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation NeurIPS 2021 Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning NeurIPS 2020 Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement Learning AISTATS 2019