ジャーナル論文 / Journal
  1. Omura, M., Osa, T., Mukuta, Y., and Harada, T., "Stabilizing Extreme Q-learning by Maclaurin Expansion", Reinforcement Learning Journal 3, 1427–1440, (2024).
  2. Chang, J., Westfectel, T., Osa, T., and Harada, T., "Offline Deep Reinforcement Learning for Visual Distractions via Domain Adversarial Training", Transactions on Machine Learning Research, (2024).
国際会議 / Proceedings
  1. Yoshikawa, S., Mukuta, Y., Osa, T., and Harada , T., "RallySim : Simulated Environment with Continuous Control for Turn-based Multi-agent Reinforcement Learning", 2nd Workshop on MAD-Games: Multi-Agent Dynamic Games, ICRA 2024, (2024).
  2. Osa, T., and Harada, T., "Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behavior and Adversarial Style Sampling for Assistive Tasks", Proceedings of the IEEE International Conferences on Robotics and Automation, 15158–15164, (2024).
  3. Osa, T., and Harada, T., "Discovering Multiple Solutions from a Single Task in Offline Reinforcement Learning", Proceedings of the 41st International Conference on Machine Learning 235, 38864–38884, (2024).
  4. Morihira, N., Deo, P., Bhadu, M., Hayashi, A., Hasegawa, T., Otsubo, S., and Osa, T., "Touch-Based Manipulation with Multi-Fingered Robot using Off-policy RL and Temporal Contrastive Learning", 2024 IEEE International Conference on Robotics and Automation (ICRA) 00, 7501–7507, (2024).
  5. Abe, H., Osa, T., Omura, M., Chang, J., and Harada, T., "Latent Space Curriculum Reinforcement Learning in High-Dimensional Contextual Spaces and Its Application to Robotic Piano Playing", 2024 IEEE-RAS 23rd International Conference on Humanoid Robots (Humanoids) 00, 266–273, (2024).