Tatsuya Matsushima - My portal

Profile Information

Affiliation: Project Researcher, The University of Tokyo

Researcher number: 90980467
ORCID ID: https://orcid.org/0000-0002-1537-7770
J-GLOBAL ID: 202301014249184399
researchmap Member ID: R000051795

Papers

M3IL: Multi-Modal Meta-Imitation Learning

Xin Zhang, Tatsuya Matsushima, Yutaka Matsuo, Yusuke Iwasawa

Transactions of the Japanese Society for Artificial Intelligence, 38(2), 2023
Collective Intelligence for 2D Push Manipulations With Mobile Robots

So Kuroki, Tatsuya Matsushima, Jumpei Arima, Hiroki Furuta, Yutaka Matsuo, Shixiang Shane Gu, Yujin Tang

IEEE Robotics and Automation Letters, 2023
World robot challenge 2020 – partner robot: a data-driven approach for room tidying with mobile manipulator

Tatsuya Matsushima, Yuki Noguchi, Jumpei Arima, Toshiki Aoki, Yuki Okita, Yuya Ikeda, Koki Ishimoto, Shohei Taniguchi, Yuki Yamashita, Shoichi Seto …

Advanced Robotics, 36(17-18) 850-869, Sep 17, 2022
Tool as Embodiment for Recursive Manipulation.

Yuki Noguchi, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu

CoRR, abs/2112.00359, 2021
Identifying Co-Adaptation of Algorithmic and Implementational Innovations in Deep Reinforcement Learning: A Taxonomy and Case Study of Inference-based Algorithms.

Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu

CoRR, abs/2103.17258, 2021
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning.

Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno, Yutaka Matsuo, Sergey Levine, Ofir Nachum, Shixiang Shane Gu

CoRR, abs/2103.12726, 2021
Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning.

Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno, Yutaka Matsuo, Sergey Levine, Ofir Nachum, Shixiang Shane Gu

Proceedings of the 38th International Conference on Machine Learning(ICML), 3541-3552, 2021
Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning

Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu

Advances in Neural Information Processing Systems, 12 9828-9842, 2021
DEPLOYMENT-EFFICIENT REINFORCEMENT LEARNING VIA MODEL-BASED OFFLINE OPTIMIZATION

Tatsuya Matsushima, Hiroki Furuta, Yutaka Matsuo, Ofir Nachum, Shixiang Shane Gu

ICLR 2021 - 9th International Conference on Learning Representations, 2021
Modeling Task Uncertainty for Safe Meta-Imitation Learning.

Tatsuya Matsushima, Naruya Kondo, Yusuke Iwasawa, Kaoru Nasuno, Yutaka Matsuo

Frontiers in robotics and AI, 7 606361-606361, 2020
Neuron as an agent

Shohei Ohsawa, Kei Akuzawa, Tatsuya Matsushima, Gustavo Bezerra, Yusuke Iwasawa, Hiroshi Kajino, Seiya Takenaka, Yutaka Matsuo

6th International Conference on Learning Representations, ICLR 2018 - Workshop Track Proceedings, 2018

Research Projects

Development of Scalable Robot Learning System for Service Robotics

Grants-in-Aid for Scientific Research, Grant-in-Aid for JSPS Fellows, Japan Society for the Promotion of Science, Apr, 2022 - Mar, 2024