Zobrazeno 1 - 10
of 466
pro vyhledávání: '"Hughes, Dana"'
This paper describes CBGT-Net, a neural network model inspired by the cortico-basal ganglia-thalamic (CBGT) circuits found in mammalian brains. Unlike traditional neural network models, which either generate an output for each provided input, or an o
Externí odkaz:
http://arxiv.org/abs/2403.15974
Autor:
Li, Huao, Chong, Yu Quan, Stepputtis, Simon, Campbell, Joseph, Hughes, Dana, Lewis, Michael, Sycara, Katia
Publikováno v:
in Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Page 180-192, ACL
While Large Language Models (LLMs) have demonstrated impressive accomplishments in both reasoning and planning, their abilities in multi-agent collaborations remains largely unexplored. This study evaluates LLM-based agents in a multi-agent cooperati
Externí odkaz:
http://arxiv.org/abs/2310.10701
Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for incorporating
Externí odkaz:
http://arxiv.org/abs/2302.12232
Autor:
Guo, Yue, Campbell, Joseph, Stepputtis, Simon, Li, Ruiyu, Hughes, Dana, Fang, Fei, Sycara, Katia
Action advising is a knowledge transfer technique for reinforcement learning based on the teacher-student paradigm. An expert teacher provides advice to a student during training in order to improve the student's sample efficiency and policy performa
Externí odkaz:
http://arxiv.org/abs/2211.07882
Autor:
Tucker, Mycal, Li, Huao, Agrawal, Siddharth, Hughes, Dana, Sycara, Katia, Lewis, Michael, Shah, Julie
Neural agents trained in reinforcement learning settings can learn to communicate among themselves via discrete tokens, accomplishing as a team what agents would be unable to do alone. However, the current standard of using one-hot vectors as discret
Externí odkaz:
http://arxiv.org/abs/2108.01828
Autor:
Zink, Jennifer, O'Connor, Sydney G., Blachman-Demner, Dara R., Wolff-Hughes, Dana L., Berrigan, David
Publikováno v:
In Journal of Adolescent Health March 2024 74(3):496-503
When developing AI systems that interact with humans, it is essential to design both a system that can understand humans, and a system that humans can understand. Most deep network based agent-modeling approaches are 1) not interpretable and 2) only
Externí odkaz:
http://arxiv.org/abs/2104.02938
Autor:
Ni, Tianwei, Li, Huao, Agrawal, Siddharth, Raja, Suhas, Jia, Fan, Gui, Yikang, Hughes, Dana, Lewis, Michael, Sycara, Katia
Teamwork is a set of interrelated reasoning, actions and behaviors of team members that facilitate common objectives. Teamwork theory and experiments have resulted in a set of states and processes for team effectiveness in both human-human and agent-
Externí odkaz:
http://arxiv.org/abs/2103.04439
Autor:
Migueles, Jairo H., Cadenas-Sanchez, Cristina, Butera, Nicole M., Bassett, David R., Wolff-Hughes, Dana L., Schrack, Jennifer A., Saint-Maurice, Pedro F., Shiroma, Eric J.
Publikováno v:
In Journal of Sport and Health Science September 2024
Autor:
Jain, Vidhi, Jena, Rohit, Li, Huao, Gupta, Tejus, Hughes, Dana, Lewis, Michael, Sycara, Katia
In a search and rescue scenario, rescuers may have different knowledge of the environment and strategies for exploration. Understanding what is inside a rescuer's mind will enable an observer agent to proactively assist them with critical information
Externí odkaz:
http://arxiv.org/abs/2011.07656