no code implementations • 24 Apr 2024 • TaeYoung Kim, Youngsoo Ha, Myungjoo Kang
Magnetohydrodynamics (MHD) plays a pivotal role in describing the dynamics of plasma and conductive fluids, essential for understanding phenomena such as the structure and evolution of stars and galaxies, and in nuclear fusion for plasma motion through ideal MHD equations.
no code implementations • 3 Jan 2024 • TaeYoung Kim, Myungjoo Kang
To this end, we developed loss functions inspired by established numerical schemes related to conservation laws and approximated numerical fluxes using Fourier neural operators (FNOs).
no code implementations • 6 Dec 2023 • TaeYoung Kim, Hongseok Yang
The recent theoretical analysis of deep neural networks in their infinite-width limits has deepened our understanding of initialisation, feature learning, and training of those networks, and brought new practical techniques for finding appropriate hyperparameters, learning network weights, and performing inference.
no code implementations • 6 Nov 2023 • Bumgeun Park, TaeYoung Kim, Quoc-Vinh Lai-Dang, Dongsoo Har
In this paper, a novel actor-critic framework namely virtual action actor-critic (VAAC), is proposed to address the challenge of efficient exploration in RL.
no code implementations • 17 Oct 2023 • Woohyeon Moon, TaeYoung Kim, Bumgeun Park, Dongsoo Har
Transformer is a state-of-the-art model in the field of natural language processing (NLP).
no code implementations • 15 Feb 2023 • Sumit Mishra, Medhavi Mishra, TaeYoung Kim, Dongsoo Har
Image inpainting is based on inpainting safe roadway elements in a roadway image, replacing accident-prone (AP) features by using a diffusion model.
no code implementations • 26 Dec 2022 • Bumgeun Park, TaeYoung Kim, Woohyeon Moon, Luiz Felipe Vecchietti, Dongsoo Har
We propose a novel method that introduces a weighting factor for each experience when calculating the loss function at the learning stage.
no code implementations • 9 Dec 2022 • Injoon Cho, Praveen Kumar Rajendran, TaeYoung Kim, Dongsoo Har
As the demand for autonomous driving increases, it is paramount to ensure safety.
no code implementations • 1 Dec 2022 • Bumgeun Park, Jihui Lee, TaeYoung Kim, Dongsoo Har
In this paper, we attempt to use the relative coordinate system (RCS) as the state for training kick-motion of robot agent, instead of using the absolute coordinate system (ACS).
no code implementations • 12 Sep 2022 • TaeYoung Kim, Myungjoo Kang
Using capacity based on these norms, we bound the generalization error of the model.
no code implementations • 31 Aug 2022 • TaeYoung Kim, Dongsoo Har
The proposed sampling strategy groups episodes with different achieved goals by using a cluster model and samples experiences in the manner of HER to create the training batch.
no code implementations • 17 Aug 2022 • Woohyeon Moon, Bumgeun Park, Sarvar Hussain Nengroo, TaeYoung Kim, Dongsoo Har
To solve this electricity consumption issue, the problem of efficient path planning for cleaning robot has become important and many studies have been conducted.
no code implementations • 13 Apr 2021 • TaeYoung Kim, Luiz Felipe Vecchietti, Kyujin Choi, Sanem Sariel, Dongsoo Har
Because these two training processes are conducted in a series in every timestep, agents can learn how to maximize role rewards and team rewards simultaneously.
Multi-agent Reinforcement Learning reinforcement-learning +2