1 code implementation • 27 Jun 2023 • Weihua Du, Jinglun Zhao, Chao Yu, Xingcheng Yao, Zimeng Song, Siyang Wu, Ruifeng Luo, Zhiyuan Liu, Xianzhong Zhao, Yi Wu
Directly applying end-to-end reinforcement learning (RL) methods to truss layout design is infeasible either, since only a tiny portion of the entire layout space is valid under the physical constraints, leading to particularly sparse rewards for RL training.
no code implementations • 19 Dec 2022 • Kangchen Zhu, Zhiliang Tian, Ruifeng Luo, Xiaoguang Mao
Since cycle construction helps to improve the style transfer ability of the model by rebuilding transferred sentences back to original-style sentences, it brings about a content loss in unsupervised text style transfer tasks.