Segui
Tatsuya Matsushima
Tatsuya Matsushima
Altri nomi松嶋 達也
Email verificata su weblab.t.u-tokyo.ac.jp - Home page
Titolo
Citata da
Citata da
Anno
Deployment-efficient reinforcement learning via model-based offline optimization
T Matsushima, H Furuta, Y Matsuo, O Nachum, S Gu
International Conference on Learning Representations, 2021
1302021
Open x-embodiment: Robotic learning datasets and rt-x models
A Padalkar, A Pooley, A Jain, A Bewley, A Herzog, A Irpan, A Khazatsky, ...
arXiv preprint arXiv:2310.08864, 2023
712023
Policy information capacity: Information-theoretic measure for task complexity in deep reinforcement learning
H Furuta, T Matsushima, T Kozuno, Y Matsuo, S Levine, O Nachum, ...
International Conference on Machine Learning, 3541-3552, 2021
182021
Co-adaptation of algorithmic and implementational innovations in inference-based deep reinforcement learning
H Furuta, T Kozuno, T Matsushima, Y Matsuo, SS Gu
Advances in neural information processing systems 34, 9828-9842, 2021
12*2021
World robot challenge 2020–partner robot: a data-driven approach for room tidying with mobile manipulator
T Matsushima, Y Noguchi, J Arima, T Aoki, Y Okita, Y Ikeda, K Ishimoto, ...
Advanced Robotics 36 (17-18), 850-869, 2022
112022
Tool as embodiment for recursive manipulation
Y Noguchi, T Matsushima, Y Matsuo, SS Gu
arXiv preprint arXiv:2112.00359, 2021
62021
Neuron as an Agent
S Ohsawa, K Akuzawa, T Matsushima, G Bezerra, Y Iwasawa, H Kajino, ...
62018
Collective intelligence for 2d push manipulations with mobile robots
S Kuroki, T Matsushima, J Arima, H Furuta, Y Matsuo, SS Gu, Y Tang
IEEE Robotics and Automation Letters 8 (5), 2820-2827, 2023
42023
Self-Recovery Prompting: Promptable General Purpose Service Robot System with Foundation Models and Self-Recovery
M Shirasaka, T Matsushima, S Tsunashima, Y Ikeda, A Horo, S Ikoma, ...
arXiv preprint arXiv:2309.14425, 2023
22023
Modeling task uncertainty for safe meta-imitation learning
T Matsushima, N Kondo, Y Iwasawa, K Nasuno, Y Matsuo
Frontiers in Robotics and AI 7, 606361, 2020
22020
Real-World Robot Applications of Foundation Models: A Review
K Kawaharazuka, T Matsushima, A Gambardella, J Guo, C Paxton, ...
arXiv preprint arXiv:2402.05741, 2024
12024
TRAIL Team Description Paper for RoboCup@ Home 2023
C Tsuji, D Komukai, M Shirasaka, H Wada, T Omija, A Horo, D Furuta, ...
arXiv preprint arXiv:2310.03913, 2023
12023
Generalizable One-shot Rope Manipulation with Parameter-Aware Policy
S Kuroki, J Guo, T Matsushima, T Okubo, M Kobayashi, Y Ikeda, ...
arXiv preprint arXiv:2306.09872, 2023
12023
学生フォーラム [第 108 回] 学生フォーラムから探る若手研究者のキャリア形成
津村賢宏, 佐久間洋司, 西村優佑, 福島康太郎, 松嶋達也
人工知能 36 (6), 794-797, 2021
12021
学生フォーラム [第 107 回] 大澤正彦先生インタビュー 「ドラえもんから紐解く人工知能・ロボット」
津村賢宏, 松嶋達也, 宮本拓
人工知能 36 (5), 654-658, 2021
12021
Pixyz: 複雑な深層生成モデル開発のためのフレームワーク
鈴木雅大, 金子貴輝, 谷口尚平, 松嶋達也, 松尾豊
人工知能学会全国大会論文集 第 33 回 (2019), 1L2J1105-1L2J1105, 2019
12019
サービスロボットシステムにおけるデータドリブンな開発工程の検討—World Robot Summit 2020 Partner Robot Challenge での事例を踏まえた考察—
松嶋達也, 野口裕貴, 有馬純平, 原田憲旺, 青木俊樹, 沖田祐樹, ...
日本ロボット学会誌 42 (2), 189-192, 2024
2024
GenDOM: Generalizable One-shot Deformable Object Manipulation with Parameter-Aware Policy
S Kuroki, J Guo, T Matsushima, T Okubo, M Kobayashi, Y Ikeda, ...
arXiv preprint arXiv:2309.09051, 2023
2023
M3IL: Multi-Modal Meta-Imitation Learning
X Zhang, T Matsushima, Y Matsuo, Y Iwasawa
Transactions of the Japanese Society for Artificial Intelligence 38 (2), A-LB3, 2023
2023
世界モデルを用いた画像・深度・触覚のマルチモーダル学習
上條達也, 石本幸暉, 松嶋達也, 岩澤有祐, 松尾豊
人工知能学会全国大会論文集 第 37 回 (2023), 2G1OS21c01-2G1OS21c01, 2023
2023
Il sistema al momento non può eseguire l'operazione. Riprova più tardi.
Articoli 1–20