Tadashi Kozuno

64 papers A* 16A 4Journal 36Unranked 3

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Am I More Pointwise or Pairwise? Revealing Position Bias in Rubric-Based LLM-as-a-Judge. CoRR Yuzheng Xu, Tosho Hirasawa, Tadashi Kozuno, Yoshitaka Ushiku
2026	J	`jnl`	LAPPI: Interactive Optimization With LLM-Assisted Preference-Based Problem Instantiation. IEEE Access So Kuroki, Manami Nakagawa, Shigeo Yoshida, Yuki Koyama, Tadashi Kozuno
2026	—	`ed.`	Neural Information Processing - 32nd International Conference, ICONIP 2025, Okinawa, Japan, November 20-24, 2025, Proceedings, Part I ICONIP (1) Tadahiro Taniguchi, Andrew Chi-Sing Leung, Tadashi Kozuno, Junichiro Yoshimoto, Mufti Mahmud, Maryam Doborjeh, Kenji Doya
2026	—	`ed.`	Neural Information Processing - 32nd International Conference, ICONIP 2025, Okinawa, Japan, November 20-24, 2025, Proceedings, Part II ICONIP (2) Tadahiro Taniguchi, Andrew Chi-Sing Leung, Tadashi Kozuno, Junichiro Yoshimoto, Mufti Mahmud, Maryam Doborjeh, Kenji Doya
2026	—	`ed.`	Neural Information Processing - 32nd International Conference, ICONIP 2025, Okinawa, Japan, November 20-24, 2025, Proceedings, Part III ICONIP (3) Tadahiro Taniguchi, Andrew Chi-Sing Leung, Tadashi Kozuno, Junichiro Yoshimoto, Mufti Mahmud, Maryam Doborjeh, Kenji Doya
2026	—	`ed.`	Neural Information Processing - 32nd International Conference, ICONIP 2025, Okinawa, Japan, November 20-24, 2025, Proceedings, Part IV ICONIP (4) Tadahiro Taniguchi, Andrew Chi-Sing Leung, Tadashi Kozuno, Junichiro Yoshimoto, Mufti Mahmud, Maryam Doborjeh, Kenji Doya
2026	—	`ed.`	Neural Information Processing - 32nd International Conference, ICONIP 2025, Okinawa, Japan, November 20-24, 2025, Proceedings, Part V ICONIP (5) Tadahiro Taniguchi, Andrew Chi-Sing Leung, Tadashi Kozuno, Junichiro Yoshimoto, Mufti Mahmud, Maryam Doborjeh, Kenji Doya
2026	J	`jnl`	WarrantScore: Modeling Warrants between Claims and Evidence for Substantiation Evaluation in Peer Reviews. CoRR Kiyotada Mori, Shohei Tanaka, Tosho Hirasawa, Tadashi Kozuno, Koichiro Yoshino, Yoshitaka Ushiku
2026	J	`jnl`	Where-to-Unmask: Ground-Truth-Guided Unmasking Order Learning for Masked Diffusion Language Models. CoRR Hikaru Asano, Tadashi Kozuno, Kuniaki Saito, Yukino Baba
2025	J	`jnl`	LAPPI: Interactive Optimization with LLM-Assisted Preference-Based Problem Instantiation. CoRR So Kuroki, Manami Nakagawa, Shigeo Yoshida, Yuki Koyama, Tadashi Kozuno
2025	J	`jnl`	MK2 at PBIG Competition: A Prompt Generation Solution. CoRR Yuzheng Xu, Tosho Hirasawa, Seiya Kawano, Shota Kato, Tadashi Kozuno
2025	A*	`conf`	Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form. ICLR Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai, Kenta Hoshino, Yohei Hosoe, Kazumi Kasaura, Masashi Hamaya, Paavo Parmas, Yutaka Matsuo
2025	J	`jnl`	Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation. CoRR Toshinori Kitamura, Arnob Ghosh, Tadashi Kozuno, Wataru Kumagai, Kazumi Kasaura, Kenta Hoshino, Yohei Hosoe, Yutaka Matsuo
2025	J	`jnl`	Self Iterative Label Refinement via Robust Unlabeled Learning. CoRR Hikaru Asano, Tadashi Kozuno, Yukino Baba
2025	J	`jnl`	Symmetry-Breaking in Multi-Agent Navigation: Winding Number-Aware MPC with a Learned Topological Strategy. CoRR Tomoki Nakao, Kazumi Kasaura, Tadashi Kozuno
2025	A*	`conf`	The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback. ICML Côme Fiegel, Pierre Ménard, Tadashi Kozuno, Michal Valko, Vianney Perchet
2024	J	`jnl`	A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees. CoRR Toshinori Kitamura, Tadashi Kozuno, Masahiro Kato, Yuki Ichihara, Soichiro Nishimori, Akiyoshi Sannai, Sho Sonoda, Wataru Kumagai, Yutaka Matsuo
2024	—	`conf`	Hand2Any: Hand-to-Any Motion Mapping with Few-Shot User Adaptation for Avatar Manipulation. ECCV Workshops (2) Riku Shinohara, Atsushi Hashimoto, Tadashi Kozuno, Shigeo Yoshida, Yutaro Hirao, Monica Perusquía-Hernández, Hideaki Uchiyama, Kiyoshi Kiyokawa
2024	—	`conf`	Hand2Any: Real-time Avatar Manipulation through Hand-to-Any Motion Mapping with Few-Shot User Adaptation. ISMAR-Adjunct Riku Shinohara, Atsushi Hashimoto, Tadashi Kozuno, Shigeo Yoshida, Yutaro Hirao, Monica Perusquía-Hernández, Hideaki Uchiyama, Kiyoshi Kiyokawa
2024	A	`conf`	Language-Guided Pattern Formation for Swarm Robotics with Multi-Agent Reinforcement Learning. IROS Hsu-Shen Liu, So Kuroki, Tadashi Kozuno, Wei-Fang Sun, Chun-Yi Lee
2024	A*	`conf`	Local and Adaptive Mirror Descents in Extensive-Form Games. NeurIPS Côme Fiegel, Pierre Ménard, Tadashi Kozuno, Rémi Munos, Vianney Perchet, Michal Valko
2024	A	`conf`	Multi-Agent Behavior Retrieval: Retrieval-Augmented Policy Training for Cooperative Push Manipulation by Mobile Robots. IROS So Kuroki, Mai Nishimura, Tadashi Kozuno
2024	J	`jnl`	Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form. CoRR Toshinori Kitamura, Tadashi Kozuno, Wataru Kumagai, Kenta Hoshino, Yohei Hosoe, Kazumi Kasaura, Masashi Hamaya, Paavo Parmas, Yutaka Matsuo
2024	A*	`conf`	Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist. ICRA Hai Nguyen, Tadashi Kozuno, Cristian C. Beltran-Hernandez, Masashi Hamaya
2024	J	`jnl`	Symmetry-aware Reinforcement Learning for Robotic Assembly under Partial Observability with a Soft Wrist. CoRR Hai Nguyen, Tadashi Kozuno, Cristian C. Beltran-Hernandez, Masashi Hamaya
2024	A*	`conf`	When to Replan? An Adaptive Replanning Strategy for Autonomous Navigation using Deep Reinforcement Learning. ICRA Kohei Honda, Ryo Yonetani, Mai Nishimura, Tadashi Kozuno
2023	A*	`conf`	Adapting to game trees in zero-sum imperfect information games. ICML Côme Fiegel, Pierre Ménard, Tadashi Kozuno, Rémi Munos, Vianney Perchet, Michal Valko
2023	J	`jnl`	Avoiding Model Estimation in Robust Markov Decision Processes with a Generative Model. CoRR Wenhao Yang, Han Wang, Tadashi Kozuno, Scott M. Jordan, Zhihua Zhang
2023	J	`jnl`	Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control With Action Constraints. IEEE Robotics Autom. Lett. Kazumi Kasaura, Shuwa Miura, Tadashi Kozuno, Ryo Yonetani, Kenta Hoshino, Yohei Hosoe
2023	J	`jnl`	Benchmarking Actor-Critic Deep Reinforcement Learning Algorithms for Robotics Control with Action Constraints. CoRR Kazumi Kasaura, Shuwa Miura, Tadashi Kozuno, Ryo Yonetani, Kenta Hoshino, Yohei Hosoe
2023	A	`conf`	Counterfactual Fairness Filter for Fair-Delay Multi-Robot Navigation. AAMAS Hikaru Asano, Ryo Yonetani, Mai Nishimura, Tadashi Kozuno
2023	J	`jnl`	Counterfactual Fairness Filter for Fair-Delay Multi-Robot Navigation. CoRR Hikaru Asano, Ryo Yonetani, Mai Nishimura, Tadashi Kozuno
2023	A*	`conf`	DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm. ICML Yunhao Tang, Tadashi Kozuno, Mark Rowland, Anna Harutyunyan, Rémi Munos, Bernardo Ávila Pires, Michal Valko
2023	J	`jnl`	DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm. CoRR Yunhao Tang, Tadashi Kozuno, Mark Rowland, Anna Harutyunyan, Rémi Munos, Bernardo Ávila Pires, Michal Valko
2023	J	`jnl`	Local and adaptive mirror descents in extensive-form games. CoRR Côme Fiegel, Pierre Ménard, Tadashi Kozuno, Rémi Munos, Vianney Perchet, Michal Valko
2023	J	`jnl`	Multi-Agent Behavior Retrieval: Retrieval-Augmented Policy Training for Cooperative Manipulation by Mobile Robots. CoRR So Kuroki, Mai Nishimura, Tadashi Kozuno
2023	A*	`conf`	Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice. ICML Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang, Nino Vieillard, Michal Valko, Wenhao Yang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári, Wataru Kumagai, Yutaka Matsuo
2023	J	`jnl`	Regularization and Variance-Weighted Regression Achieves Minimax Optimality in Linear MDPs: Theory and Practice. CoRR Toshinori Kitamura, Tadashi Kozuno, Yunhao Tang, Nino Vieillard, Michal Valko, Wenhao Yang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári, Wataru Kumagai, Yutaka Matsuo
2023	J	`jnl`	When to Replan? An Adaptive Replanning Strategy for Autonomous Navigation using Deep Reinforcement Learning. CoRR Kohei Honda, Ryo Yonetani, Mai Nishimura, Tadashi Kozuno
2022	J	`jnl`	Adapting to game trees in zero-sum imperfect information games. CoRR Côme Fiegel, Pierre Ménard, Tadashi Kozuno, Rémi Munos, Vianney Perchet, Michal Valko
2022	A*	`conf`	Confident Approximate Policy Iteration for Efficient Local Planning in $q^\pi$-realizable MDPs. NeurIPS Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári
2022	J	`jnl`	Confident Approximate Policy Iteration for Efficient Local Planning in q CoRR Gellért Weisz, András György, Tadashi Kozuno, Csaba Szepesvári
2022	—	`conf`	Deep Learning-based Nonlinear Quantizer for Fronthaul Compression. OECC/PSC Shinnosuke Yagi, Mutsuki Nakahara, Kosuke Suzuoki, Tadashi Kozuno, Daisuke Hisano
2022	J	`jnl`	Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences. J. Mach. Learn. Res. Alan Chan, Hugo Silva, Sungsu Lim, Tadashi Kozuno, A. Rupam Mahmood, Martha White
2022	J	`jnl`	KL-Entropy-Regularized RL with a Generative Model is Minimax Optimal. CoRR Tadashi Kozuno, Wenhao Yang, Nino Vieillard, Toshinori Kitamura, Yunhao Tang, Jincheng Mei, Pierre Ménard, Mohammad Gheshlaghi Azar, Michal Valko, Rémi Munos, Olivier Pietquin, Matthieu Geist, Csaba Szepesvári
2022	J	`jnl`	No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL. CoRR Han Wang, Archit Sakhadeo, Adam White, James Bell, Vincent Liu, Xutong Zhao, Puer Liu, Tadashi Kozuno, Alona Fyshe, Martha White
2022	J	`jnl`	No More Pesky Hyperparameters: Offline Hyperparameter Tuning for RL. Trans. Mach. Learn. Res. Han Wang, Archit Sakhadeo, Adam M. White, James Bell, Vincent Liu, Xutong Zhao, Puer Liu, Tadashi Kozuno, Alona Fyshe, Martha White
2022	A*	`conf`	Variational oracle guiding for reinforcement learning. ICLR Dongqi Han, Tadashi Kozuno, Xufang Luo, Zhao-Yun Chen, Kenji Doya, Yuqing Yang, Dongsheng Li
2021	A*	`conf`	Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning. NeurIPS Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu
2021	J	`jnl`	Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences. CoRR Alan Chan, Hugo Silva, Sungsu Lim, Tadashi Kozuno, A. Rupam Mahmood, Martha White
2021	J	`jnl`	Identifying Co-Adaptation of Algorithmic and Implementational Innovations in Deep Reinforcement Learning: A Taxonomy and Case Study of Inference-based Algorithms. CoRR Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu
2021	A*	`conf`	Learning in two-player zero-sum partially observable Markov games with perfect recall. NeurIPS Tadashi Kozuno, Pierre Ménard, Rémi Munos, Michal Valko
2021	J	`jnl`	Model-Free Learning for Two-Player Zero-Sum Partially Observable Markov Games with Perfect Recall. CoRR Tadashi Kozuno, Pierre Ménard, Rémi Munos, Michal Valko
2021	A*	`conf`	Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning. ICML Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno, Yutaka Matsuo, Sergey Levine, Ofir Nachum, Shixiang Shane Gu
2021	J	`jnl`	Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning. CoRR Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno, Yutaka Matsuo, Sergey Levine, Ofir Nachum, Shixiang Shane Gu
2021	A*	`conf`	Revisiting Peng's Q(λ) for Modern Reinforcement Learning. ICML Tadashi Kozuno, Yunhao Tang, Mark Rowland, Rémi Munos, Steven Kapturowski, Will Dabney, Michal Valko, David Abel
2021	J	`jnl`	Revisiting Peng's Q(λ) for Modern Reinforcement Learning. CoRR Tadashi Kozuno, Yunhao Tang, Mark Rowland, Rémi Munos, Steven Kapturowski, Will Dabney, Michal Valko, David Abel
2021	A*	`conf`	Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation. NeurIPS Yunhao Tang, Tadashi Kozuno, Mark Rowland, Rémi Munos, Michal Valko
2021	J	`jnl`	Unifying Gradient Estimators for Meta-Reinforcement Learning via Off-Policy Evaluation. CoRR Yunhao Tang, Tadashi Kozuno, Mark Rowland, Rémi Munos, Michal Valko
2020	A*	`conf`	Leverage the Average: an Analysis of KL Regularization in Reinforcement Learning. NeurIPS Nino Vieillard, Tadashi Kozuno, Bruno Scherrer, Olivier Pietquin, Rémi Munos, Matthieu Geist
2020	J	`jnl`	Leverage the Average: an Analysis of Regularization in RL. CoRR Nino Vieillard, Tadashi Kozuno, Bruno Scherrer, Olivier Pietquin, Rémi Munos, Matthieu Geist
2019	J	`jnl`	Gap-Increasing Policy Evaluation for Efficient and Noise-Tolerant Reinforcement Learning. CoRR Tadashi Kozuno, Dongqi Han, Kenji Doya
2019	A	`conf`	Theoretical Analysis of Efficiency and Robustness of Softmax and Gap-Increasing Operators in Reinforcement Learning. AISTATS Tadashi Kozuno, Eiji Uchibe, Kenji Doya
2017	J	`jnl`	Unifying Value Iteration, Advantage Learning, and Dynamic Policy Programming. CoRR Tadashi Kozuno, Eiji Uchibe, Kenji Doya