Our paper was accepted for NeurIPS2022 (Spotlight)

Our paper was accepted for presentation at NeurIPS2022 (Spotlight) . ◼︎書誌情報 Hiroki Furuta, Yutaka Matsuo, Shixiang Shane Gu. “Generalized Decision Transformer for Offline Hindsight Information Matching”,  International Conference on Learning Representations (ICLR2022). ◼︎概要 How to extract as much learning signal from each trajectory data has been a key problem in reinforcement learning (RL), where sample…

当研究室の論文が人工知能学会論文誌に採録されました

◼Information タイトル:Transformerと自己教師あり学習を用いたシーン解釈手法の提案 著 者: 小林 由弥 鈴木 雅大 松尾 豊 掲載号:第37巻2号 J-STAGE ◼Overview Ability to understand surrounding environment based on its components, namely objects, is one of the most important cognitive ability for intelligent agents. Human beings are able to decompose sensory input, i.e. visual stimulation, into some components based on its meaning or relationships between…

Our paper was accepted for NeurIPS2021 (Spotlight)

Our paper was accepted for presentation at NeurIPS2021 (Spotlight) . ︎書誌情報 Yusuke Iwasawa, Yutaka Matsuo. “Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization”,  Advances in Neural Information Processing Systems 2021 (NeurIPS2021). ︎概要 This paper presents a new algorithm for domain generalization (DG), test-time template adjuster (T3A), aiming to develop a model that performs well under conditions…

Our paper was accepted for NeurIPS2021

Our paper was accepted for presentation at NeurIPS2021 . ︎書誌情報 Hiroki Furuta, Tadashi Kozuno, Tatsuya Matsushima, Yutaka Matsuo, and Shixiang Shane Gu. “Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning”,  Advances in Neural Information Processing Systems 2021 (NeurIPS2021). ︎概要 Recently many algorithms were devised for reinforcement learning (RL) with function approximation. While…

Our paper was accepted for ICML2021.

【Information】 Hiroki Furuta, Tatsuya Matsushima, Tadashi Kozuno, Yutaka Matsuo, Sergey Levine, Ofir Nachum, and Shixiang Shane Gu. “Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning”, International Conference on Machine Learning 2021 (ICML2021). July 2021. 【Overview】 Progress in deep reinforcement learning (RL) research is largely enabled by benchmark task environments. However, analyzing…

Our paper was accepted for EMNLP2020.

Our paper was accepted to the main conference at EMNLP 2020. 【Information】Our paper was accepted to the main conference at EMNLP 2020 【Title】VCDM: Leveraging Variational Bi-encoding and Deep Contextualized Word Representations for Improved Definition Modeling 【Authors】Machel Reid, Edison Marrese-Taylor, Yutaka Matsuo 【Overview】In this paper, we tackle the task of definition modeling, where the goal is…