Efficient Exploration with Failure Ratio for Deep Reinforcement LearningMinori NaritaDaiki Kimura2020AAAI 2020
Learning Neuro-Symbolic World Models with Conversational ProprioceptionDon Joven Ravoy AgravanteDaiki Kimuraet al.2023ACL 2023
Neuro-Symbolic Reinforcement Learning with First-Order LogicDaiki KimuraMasaki Onoet al.2021EMNLP 2021
Neuro-Symbolic Approaches for Text-Based Policy LearningSUBHAJIT CHAUDHURYPrithvi Senet al.2021EMNLP 2021
Bootstrapped Q-learning with Context Relevant Observation Pruning to Generalize in Text-based GameSUBHAJIT CHAUDHURYDaiki Kimuraet al.2020EMNLP 2020
Domain-adaptive Instance Segmentation for Visual Inspection from Civil Infrastructure ImagesTakayuki KatsukiHaoxiang Qiuet al.2024MIRU 2024
TOWARDS EFFICIENT SATELLITE DATA REPRESENTATION LEARNING WITH CONSISTENCY LOSSNaomi SimumbaDaiki Kimuraet al.2024IGARSS 2024
A cycle consistency based Approach for Semantic Segmentation on crack imagesHaoxiang QiuTomoya Sakaiet al.2024SSII 2024