Ryo Iwaki

11 papers Journal 7Unranked 4
YearRankTypeTitle / Venue / Authors
2026 J jnl
Distorted Distributional Policy Evaluation for Offline Reinforcement Learning.
CoRR
Ryo Iwaki, Takayuki Osogami
2026 J jnl
Toward Incorporating mmWave Beam Tracking for Connected Autonomous Vehicles.
IEEE Access
Jin Nakazato, Kazuki Maruta, Ryo Iwaki, Sojin Ozawa, Yuki Sasaki, Tetsuya Iye, Zongdian Li, Rui Dinis
2025 J jnl
Mirror Descent Actor Critic via Bounded Advantage Learning.
CoRR
Ryo Iwaki
2024 — conf
Millimeter-Wave Fast Beam Tracking Enabled by RAN/V2X Cooperation.
ICAIIC
Kazuki Maruta, Jin Nakazato, Kengo Suzuki, Dou Hu, Ryo Iwaki, Sojin Ozawa, Yuki Sasaki, Hideya So, Manabu Tsukada
2024 — conf
Optimizing mmWave Beamforming for High-Speed Connected Autonomous Vehicles: An Adaptive Approach.
CCNC
Ryo Iwaki, Jin Nakazato, Muhammad Asad, Ehsan Javanmardi, Kazuki Maruta, Manabu Tsukada, Hideya Ochiai, Hiroshi Esaki
2019 J jnl
Implicit incremental natural actor critic algorithm.
Neural Networks
Ryo Iwaki, Minoru Asada
2019 J jnl
Situated GAIL: Multitask imitation using task-conditioned adversarial inverse reinforcement learning.
CoRR
Kyoichiro Kobayashi, Takato Horii, Ryo Iwaki, Yukie Nagai, Minoru Asada
2018 J jnl
Incremental Estimation of Natural Policy Gradient with Relative Importance Weighting.
IEICE Trans. Inf. Syst.
Ryo Iwaki, Hiroki Yokoyama, Minoru Asada
2017 — conf
Implicit Incremental Natural Actor Critic.
ICONIP (1)
Ryo Iwaki, Minoru Asada
2017 J jnl
On- and Off-Policy Monotonic Policy Improvement.
CoRR
Ryo Iwaki, Minoru Asada
2014 — conf
Adaptive leader-follower role switching based on rhythm stability: Toward modeling of dynamic infant-caregiver interaction.
ICDL-EPIROB
Ryo Iwaki, Hideyuki Takahashi, Minoru Asada