Zobrazeno 1 - 10
of 755
pro vyhledávání: '"Zhang,Xingyuan"'
Incorporating the successful paradigm of pretraining and finetuning from Computer Vision and Natural Language Processing into decision-making has become increasingly popular in recent years. In this paper, we study Imitation Learning from Observation
Externí odkaz:
http://arxiv.org/abs/2404.18896
Unlike most reinforcement learning agents which require an unrealistic amount of environment interactions to learn a new behaviour, humans excel at learning quickly by merely observing and imitating others. This ability highly depends on the fact tha
Externí odkaz:
http://arxiv.org/abs/2312.02019
Autor:
Cao, Yuanyuan, Hu, Yulian, Lei, Fang, Zhang, Xingyuan, Liu, Weifang, Huang, Xuewei, Sun, Tao, Lin, Lijin, Yi, Maolin, Li, Yuping, Zhang, Jinpeng, Li, Yaping, Wang, Guoping, Cheng, Zhonghua
Publikováno v:
In Bone October 2024 187
Autor:
Gong, Jing, Zhang, Xingyuan, Liang, Rongyao, Ma, Juanqiong, Yang, Na, Cai, Kaiwei, Wu, Jinyun, Xie, Zhiyong, Zhang, Shusheng, Chen, Yanlong, Liao, Qiongfeng
Publikováno v:
In Food Chemistry 30 July 2024 447
Autor:
Gong, Jing, Chen, Yanlong, A., Wenwei, Zhang, Xingyuan, Ma, Juanqiong, Xie, Zhiyong, Li, Pei, Huang, Aihua, Zhang, Shusheng, Liao, Qiongfeng
Publikováno v:
In Journal of Hazardous Materials 5 July 2024 472
Publikováno v:
In Ceramics International 1 June 2024 50(11) Part A:19148-19162
Autor:
Chen, Yanlong, Zhang, Xingyuan, Ma, Juanqiong, Gong, Jing, A, Wenwei, Huang, Xinyu, Li, Pei, Xie, Zhiyong, Li, Gongke, Liao, Qiongfeng
Publikováno v:
In Journal of Hazardous Materials 5 March 2024 465
Autor:
He, Bingqiang, Niu, Li, Li, Shaolan, Li, Hui, Hou, Yuxuan, Li, Aicheng, Zhang, Xingyuan, Hao, Huifei, Song, Honghua, Cai, Rixin, Zhou, Yue, Wang, Yingjie, Wang, Yongjun
Publikováno v:
In Brain Behavior and Immunity February 2024 116:85-100
Autor:
Qin, Rongjun, Gao, Songyi, Zhang, Xingyuan, Xu, Zhen, Huang, Shengkai, Li, Zewen, Zhang, Weinan, Yu, Yang
Offline reinforcement learning (RL) aims at learning a good policy from a batch of collected data, without extra interactions with the environment during training. However, current offline RL benchmarks commonly have a large reality gap, because they
Externí odkaz:
http://arxiv.org/abs/2102.00714
Most existing dehazing algorithms often use hand-crafted features or Convolutional Neural Networks (CNN)-based methods to generate clear images using pixel-level Mean Square Error (MSE) loss. The generated images generally have better visual appeal,
Externí odkaz:
http://arxiv.org/abs/1911.09389