Research
Publications
Category
Research Area
Year
-
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, and Shixiang Shane Gu
International Conference on Machine Learning 2021 (ICML2021).
-
Identifying Co-Adaptation of Algorithmic and implementational Innovations in Deep Reinforcement Learning: Taxonomy of Inference-based Algorithms
Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, Shixiang Shane Gu.
International Conference on Machine Learning 2021 (ICML2021).
-
Reward and Optimality Empowerments: Information-Theoretic Measures for Task Complexity in Deep Reinforcement Learning
Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno, Yutaka Matsuo, Sergey Levine, Ofir Nachum, and Shixiang Shane Gu.
International Conference on Machine Learning 2021 (ICML2021). July 2021. [paper]
-
Group Equivariant Conditional Neural Processes
Makoto Kawano, Wataru Kumagai, Akiyoshi Sannai, Yusuke Iwasawa, and Yutaka Matsuo.
International Conference on Learning Representations 2021 (ICLR2021).
-
JSAI2020 Student Incentive Award, “Continuous Learning Based on Amortized Reasoning.”
川島 寛乃，河野 慎，熊谷 亘, 松井 孝太，中澤 仁
-
Semi-supervised Multimodal Learning with Deep Generative Models
鈴木雅大, 松尾豊
情報処理学会論文誌, Vol. 59, No. 12 (2018)
-
user hostile network
岩澤有祐, 矢入郁子, 松尾豊
人工知能学会論文誌, Vol. 32, No. 4, pp. A-GB5_1-12 (2017)
-
User adaptation of action recognition models based on deep learning with semi-supervised distillation
岩澤有祐, 矢入郁子, 松尾豊
人工知能学会論文誌, Vol. 32, No. 4, pp. A-G82_1-11 (2017)
-
Zero-shot learning considering observation probabilities for each attribute
鈴木 雅大, 佐藤 晴彦, 小山 聡, 栗原 正仁, 松尾 豊
情報処理学会論文誌, Vol. 57, No. 5, pp. 1499-1513 (2016)