1 code implementation • 6 Oct 2023 • Heehyeon Kim, Jinhyeok Choi, Joyce Jiyoung Whang
We address this problem using Graph Neural Networks (GNNs) by proposing a dynamic relation-attentive aggregation mechanism.
no code implementations • 24 Aug 2023 • Yunho Kim, Hyunsik Oh, Jeonghyun Lee, Jinhyeok Choi, Gwanghyeon Ji, Moonkyu Jung, Donghoon Youm, Jemin Hwangbo
In this work, we propose a novel reinforcement learning framework for training neural network controllers for complex robotic systems consisting of both rewards and constraints.