Zobrazeno 1 - 10
of 1 211
pro vyhledávání: '"Tung, M"'
Recent work in offline reinforcement learning (RL) has demonstrated the effectiveness of formulating decision-making as return-conditioned supervised learning. Notably, the decision transformer (DT) architecture has shown promise across various domai
Externí odkaz:
http://arxiv.org/abs/2410.03408
Recent studies reveal that well-performing reinforcement learning (RL) agents in training often lack resilience against adversarial perturbations during deployment. This highlights the importance of building a robust agent before deploying it in the
Externí odkaz:
http://arxiv.org/abs/2410.03376
Reinforcement Learning (RL) agents demonstrating proficiency in a training environment exhibit vulnerability to adversarial perturbations in input observations during deployment. This underscores the importance of building a robust agent before its r
Externí odkaz:
http://arxiv.org/abs/2408.00023
Publikováno v:
International Conference on Pattern Recognition and Artificial Intelligence (ICPRAI) 2024
Offline reinforcement learning (RL) addresses the challenge of expensive and high-risk data exploration inherent in RL by pre-training policies on vast amounts of offline data, enabling direct deployment or fine-tuning in real-world environments. How
Externí odkaz:
http://arxiv.org/abs/2405.11206
Autor:
Thong M. Pham, Harrison Hyde, Maw K. Kaung, Yan Zhuge, Duong T. Tran, Des Vlietstra, Tung M. Tran
Publikováno v:
Defence Technology, Vol 40, Iss , Pp 138-153 (2024)
Polypropylene (PP) fibres have primarily used to control shrinkage cracks or mitigate explosive spalling in concrete structures exposed to fire or subjected to impact/blast loads, with limited investigations on capacity improvement. This study unveil
Externí odkaz:
https://doaj.org/article/dd60e4c0d2a6439e87307a322257011b
Publikováno v:
International Journal of Concrete Structures and Materials, Vol 18, Iss 1, Pp 1-15 (2024)
Abstract This study investigated the effect of rubber content on the mechanical characteristics of ultra-high-performance rubberised concrete (UHPRuC). The results revealed a distinctive non-linear decrease in the dry density of UHPRuC as the rubber
Externí odkaz:
https://doaj.org/article/6beefbeeb6014aa886e6f855d1664b8d
This paper considers a network referred to as SoftGroup for accurate and scalable 3D instance segmentation. Existing state-of-the-art methods produce hard semantic predictions followed by grouping instance segmentation results. Unfortunately, errors
Externí odkaz:
http://arxiv.org/abs/2209.08263
Existing state-of-the-art 3D instance segmentation methods perform semantic segmentation followed by grouping. The hard predictions are made when performing semantic segmentation such that each point is associated with a single class. However, the er
Externí odkaz:
http://arxiv.org/abs/2203.01509
Influence of preloading on dynamic compressive behaviour and properties of fibre reinforced concrete
Publikováno v:
In Structures November 2024 69