Zobrazeno 1 - 10
of 926
pro vyhledávání: '"He, An Zhi"'
When querying a large language model (LLM), the context, i.e. personal, demographic, and cultural information specific to an end-user, can significantly shape the response of the LLM. For example, asking the model to explain Newton's second law with
Externí odkaz:
http://arxiv.org/abs/2405.01768
Our ultimate goal is to build robust policies for robots that assist people. What makes this hard is that people can behave unexpectedly at test time, potentially interacting with the robot outside its training distribution and leading to failures. E
Externí odkaz:
http://arxiv.org/abs/2310.10610
Publikováno v:
Communications Physics. 11/6/2024, Vol. 7 Issue 1, p1-12. 12p.
Recent work in sim2real has successfully enabled robots to act in physical environments by training in simulation with a diverse ''population'' of environments (i.e. domain randomization). In this work, we focus on enabling generalization in assistiv
Externí odkaz:
http://arxiv.org/abs/2212.03175
Publikováno v:
In Aerospace Science and Technology December 2024 155 Part 1
Publikováno v:
In Acta Astronautica December 2024 225:402-416
Publikováno v:
In Journal of Molecular Structure 15 February 2025 1322 Part 2
Learning policies via preference-based reward learning is an increasingly popular method for customizing agent behavior, but has been shown anecdotally to be prone to spurious correlations and reward hacking behaviors. While much prior work focuses o
Externí odkaz:
http://arxiv.org/abs/2204.06601
Autor:
He, Jerry Zhi-Yang, Dragan, Anca D.
Real-world robotic tasks require complex reward functions. When we define the problem the robot needs to solve, we pretend that a designer specifies this complex reward exactly, and it is set in stone from then on. In practice, however, reward design
Externí odkaz:
http://arxiv.org/abs/2111.09884
Autor:
Gao, Tao, Hu, Sheng-lin, Yan, Rui, He, Ling-zhi, Fang, Nan, Zhang, Zhong-hao, Duan, Zhi-hao, Tang, Zi-zhong, Chen, Yang-er, Yuan, Shu, Ye, Lin, Yan, Xiao-rong, Yuan, Ming
Publikováno v:
In Arabian Journal of Chemistry June 2024 17(6)