基于多智能体强化学习的博弈综述
李艺春， 刘泽娇， 洪艺天， 王继超， 王健瑞， 李毅， 唐漾 - 自动化学报, 2024 - aas.net.cn
多智能体强化学习作为博弈论, 控制论和多智能体学习的交叉研究领域, 是多智能体系统研究中
的前沿方向, 赋予了智能体在动态多维的复杂环境中通过交互和决策完成多样化任务的能力 …
的前沿方向, 赋予了智能体在动态多维的复杂环境中通过交互和决策完成多样化任务的能力 …
Don't Let Your Robot be Harmful: Responsible Robotic Manipulation
Unthinking execution of human instructions in robotic manipulation can lead to severe safety
risks, such as poisonings, fires, and even explosions. In this paper, we present responsible …
risks, such as poisonings, fires, and even explosions. In this paper, we present responsible …
On the Limit of Language Models as Planning Formalizers
C Huang, L Zhang - arXiv preprint arXiv:2412.09879, 2024 - arxiv.org
Large Language Models have been shown to fail to create executable and verifiable plans
in grounded environments. An emerging line of work shows success in using LLM as a …
in grounded environments. An emerging line of work shows success in using LLM as a …
Benchmark Real-time Adaptation and Communication Capabilities of Embodied Agent in Collaborative Scenarios
Advancements in Large Language Models (LLMs) have opened transformative possibilities
for human-robot interaction, especially in collaborative environments. However, Real-time …
for human-robot interaction, especially in collaborative environments. However, Real-time …