Motoki Omura

11 papers A* 2Journal 8Unranked 1

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Resource-Efficient Model-Free Reinforcement Learning for Board Games. CoRR Kazuki Ota, Takayuki Osa, Motoki Omura, Tatsuya Harada
2026	J	`jnl`	Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning. CoRR Naoki Shitanda, Motoki Omura, Tatsuya Harada, Takayuki Osa
2025	A*	`conf`	Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning. ICML Motoki Omura, Kazuki Ota, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada
2025	J	`jnl`	Gradual Transition from Bellman Optimality Operator to Bellman Operator in Online Reinforcement Learning. CoRR Motoki Omura, Kazuki Ota, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada
2025	J	`jnl`	Offline Reinforcement Learning with Wasserstein Regularization via Optimal Transport Maps. CoRR Motoki Omura, Yusuke Mukuta, Kazuki Ota, Takayuki Osa, Tatsuya Harada
2024	J	`jnl`	Entropy Controllable Direct Preference Optimization. CoRR Motoki Omura, Yasuhiro Fujita, Toshiki Kataoka
2024	—	`conf`	Latent Space Curriculum Reinforcement Learning in High-Dimensional Contextual Spaces and Its Application to Robotic Piano Playing. Humanoids Haruki Abe, Takayuki Osa, Motoki Omura, Jen-Yen Chang, Tatsuya Harada
2024	J	`jnl`	Stabilizing Extreme Q-learning by Maclaurin Expansion. RLJ Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada
2024	J	`jnl`	Stabilizing Extreme Q-learning by Maclaurin Expansion. CoRR Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada
2024	A*	`conf`	Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning. AAAI Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada
2024	J	`jnl`	Symmetric Q-learning: Reducing Skewness of Bellman Error in Online Reinforcement Learning. CoRR Motoki Omura, Takayuki Osa, Yusuke Mukuta, Tatsuya Harada