Follow
Kei Ota
Kei Ota
Tokyo Institute of Technology, Mitsubishi Electric
Verified email at ds.MitsubishiElectric.co.jp - Homepage
Title
Cited by
Cited by
Year
Trajectory Optimization for Unknown Constrained Systems using Reinforcement Learning
K Ota, DK Jha, T Oiki, M Miura, T Nammoto, D Nikovski, T Mariyama
IROS2019, 2019
242019
Efficient Exploration in Constrained Environments with Goal-Oriented Reference Path
K Ota, Y Sasaki, DK Jha, Y Yoshiyasu, A Kanezaki
IROS2020, 2020
162020
Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?
K Ota, T Oiki, DK Jha, T Mariyama, D Nikovski
ICML2020, 2020
142020
Training larger networks for deep reinforcement learning
K Ota, DK Jha, A Kanezaki
arXiv preprint arXiv:2102.07920, 2021
92021
Data-efficient learning for complex and real-time physical problem solving using augmented simulation
K Ota, DK Jha, D Romeres, J van Baar, KA Smith, T Semitsu, T Oiki, ...
IEEE Robotics and Automation Letters 6 (2), 4241-4248, 2021
62021
tf2rl
K Ota
https://github.com/keiohta/tf2rl, 2020
62020
Deep Reactive Planning in Dynamic Environments
K Ota, DK Jha, T Onishi, A Kanezaki, Y Yoshiyasu, Y Sasaki, T Mariyama, ...
CoRL2020, 2020
42020
Fault Tolerant Circuit Design for Low-cost and Multi-Functional Attitude Sensor Using Real-time Image Recognition
Y Kikuya, M Matsushita, M Koga, K Ohta, Y Hayashi, T Koike, T Ozawa, ...
31st International Symposium on Space Technology and Science, 3-9, 2017
42017
OPIRL: Sample efficient off-policy inverse reinforcement learning via distribution matching
H Hoshino, K Ota, A Kanezaki, R Yokota
2022 International Conference on Robotics and Automation (ICRA), 448-454, 2022
22022
Towards Human-Level Learning of Complex Physical Puzzles
K Ota, DK Jha, D Romeres, J van Baar, KA Smith, T Semitsu, T Oiki, ...
RAL+ICRA2021, 2020
22020
Object Memory Transformer for Object Goal Navigation
R Fukushima, K Ota, A Kanezaki, Y Sasaki, Y Yoshiyasu
arXiv preprint arXiv:2203.14708, 2022
12022
What We Learned from the Tokyo Tech 50 kg-satellite" TSUBAME"
Y Yatsu, N Kawai, S KIMURA, M MATSUSHITA, S KAWAJIRI, K TAWARA, ...
12017
深層学習を応用した革新的姿勢センサの実証
谷津陽一, 吉井健敏, 村木雄太郎, 針田聖平, 太田佳, 松下将典, ...
宇宙科学技術連合講演会講演集 60, 6p, 2016
12016
深層学習を用いた軌道上実時間衛星画像分類
太田佳, 谷津陽一, 松永三郎
宇宙科学技術連合講演会講演集 60, 6p, 2016
12016
Development of a micro-satellite TSUBAME for X-ray polarimetry of GRBs
S Kurita, H Ohuchi, M Arimoto, Y Yatsu, N Kawai, K Ohta, M Koga, EG Kim, ...
arXiv preprint arXiv:1503.01975, 2015
12015
ロボットの動作生成のための強化学習
太田佳
人工知能 37 (4), 499-506, 2022
2022
Moving object control device, moving object control learning device, and moving object control method
K Ota, T Nammoto
US Patent App. 17/297,881, 2022
2022
動的環境下におけるロボットの動作生成
太田佳, 金崎朝子
日本ロボット学会誌 39 (7), 581-586, 2021
2021
Q-Learning を用いた無線メッシュネットワークの通信性能評価 (安全・安心な生活と ICT)
小林卓矢, 澤健太郎, 角武憲, 太田佳, 山内尚久
電子情報通信学会技術研究報告= IEICE technical report: 信学技報 119 (226), 23-28, 2019
2019
強化学習の基礎と実用化に向けた課題
毬山利貞, 太田佳
映像情報メディア学会誌 73 (2), 265-270, 2019
2019
The system can't perform the operation now. Try again later.
Articles 1–20