Zobrazeno 1 - 10
of 340
pro vyhledávání: '"Hu, Siyi"'
Autor:
Hu, Siyi, Arroyo, Diego Martin, Debats, Stephanie, Manhardt, Fabian, Carlone, Luca, Tombari, Federico
Realistic conditional 3D scene synthesis significantly enhances and accelerates the creation of virtual environments, which can also provide extensive training data for computer vision and robotics research among other applications. Diffusion models
Externí odkaz:
http://arxiv.org/abs/2405.21066
The Internet and social media have altered how individuals access news in the age of instantaneous information distribution. While this development has increased access to information, it has also created a significant problem: the spread of fake new
Externí odkaz:
http://arxiv.org/abs/2308.16328
Autor:
Zhang, Ceyao, Yang, Kaijie, Hu, Siyi, Wang, Zihao, Li, Guanghe, Sun, Yihang, Zhang, Cheng, Zhang, Zhaowei, Liu, Anji, Zhu, Song-Chun, Chang, Xiaojun, Zhang, Junge, Yin, Feng, Liang, Yitao, Yang, Yaodong
Building agents with adaptive behavior in cooperative tasks stands as a paramount goal in the realm of multi-agent systems. Current approaches to developing cooperative agents rely primarily on learning-based methods, whose policy generalization depe
Externí odkaz:
http://arxiv.org/abs/2308.11339
Multi-agent reinforcement learning (MARL) has been shown effective for cooperative games in recent years. However, existing state-of-the-art methods face challenges related to sample complexity, training instability, and the risk of converging to a s
Externí odkaz:
http://arxiv.org/abs/2306.10715
Autor:
Hughes, Nathan, Chang, Yun, Hu, Siyi, Talak, Rajat, Abdulhai, Rumaisa, Strader, Jared, Carlone, Luca
3D spatial perception is the problem of building and maintaining an actionable and persistent representation of the environment in real-time using sensor data and prior knowledge. Despite the fast-paced progress in robot perception, most existing met
Externí odkaz:
http://arxiv.org/abs/2305.07154
The necessity for cooperation among intelligent machines has popularised cooperative multi-agent reinforcement learning (MARL) in AI research. However, many research endeavours heavily rely on parameter sharing among agents, which confines them to on
Externí odkaz:
http://arxiv.org/abs/2304.09870
Autor:
Hu, Siyi, Zhong, Yifan, Gao, Minquan, Wang, Weixun, Dong, Hao, Liang, Xiaodan, Li, Zhihui, Chang, Xiaojun, Yang, Yaodong
A significant challenge facing researchers in the area of multi-agent reinforcement learning (MARL) pertains to the identification of a library that can offer fast and compatible development for multi-agent tasks and algorithm combinations, while obv
Externí odkaz:
http://arxiv.org/abs/2210.13708
Abstract semantic 3D scene understanding is a problem of critical importance in robotics. As robots still lack the common-sense knowledge about household objects and locations of an average human, we investigate the use of pre-trained language models
Externí odkaz:
http://arxiv.org/abs/2209.05629
Semantic 3D scene understanding is a problem of critical importance in robotics. While significant advances have been made in simultaneous localization and mapping algorithms, robots are still far from having the common sense knowledge about househol
Externí odkaz:
http://arxiv.org/abs/2206.04585
Cooperative multi-agent reinforcement learning (MARL) is making rapid progress for solving tasks in a grid world and real-world scenarios, in which agents are given different attributes and goals, resulting in different behavior through the whole mul
Externí odkaz:
http://arxiv.org/abs/2207.05683