Autonomous agents are able to draw on a wide variety of potential sources of task knowledge; however current approaches invariably focus on only one or two. Here we investigate the challenges and impact of exploiting diverse knowledge sources to learn online, in one-shot, new tasks for a simulated office mobile robot. The resulting agent, developed in the Soar cognitive architecture, uses the following sources of domain and task knowledge: interaction with the environment, task execution and search knowledge, human natural language instruction, and responses retrieved from a large language model (GPT-3). We explore the distinct contributions of these knowledge sources and evaluate the performance of different combinations in terms of learning correct task knowledge and human workload. Results show that an agent's online integration of diverse knowledge sources improves one-shot task learning overall, reducing human feedback needed for rapid and reliable task learning.
Cognitive-Mental-LLM: Evaluating Reasoning in Large Language Models for Mental Health Prediction via Online Text
Ira A. Fulton Schools of Engineering Arizona State University Tempe, USA(伊拉·A·福林工程学校亚利桑那州立大学Tempe分校);Department of Psychology Santa Clara University Santa Clara, USA(心理学系圣克拉拉大学Santa Clara分校)
Preliminary Investigations of a Multi-Faceted Robust and Synergistic Approach in Semiconductor Electron Micrograph Analysis: Integrating Vision Transformers with Large Language and Multimodal Models
Green Offloading in Fog-Assisted IoT Systems: An Online Perspective Integrating Learning and Control
School of Information Science and Technology, ShanghaiTech University(上海科技大学信息科学与技术学院)
在雾辅助物联网系统中,通常的做法是将任务从物联网设备卸载到其附近的雾节点,以减少任务处理延迟和能耗。然而,在线节能方案的设计仍然是一个开放的问题,因为各种不确定性的系统动力学,如处理能力和传输速率。此外,决策过程受到雾节点和物联网设备资源限制的约束,使设计更加复杂。在本文中,我们制定这样的任务卸载问题与未知的系统动力学作为一个组合的多臂强盗(CMAB)问题的长期约束的时间平均能耗。通过在线学习和在线控制的有效结合,我们提出了一个\textit{Learning-Aided Green Offloading}(LAGO)计划。在LAGO中,我们采用强盗学习方法来处理开发探索权衡,并利用虚拟队列技术来处理长期约束。我们的理论分析表明,LAGO可以减少平均任务延迟与一个可调的次线性遗憾界在有限的时间范围内,并满足长期的时间平均能量约束。我们进行了大量的模拟来验证这些理论结果。
Intent-Driven Smart Manufacturing Integrating Knowledge Graphs and Large Language Models
1Department of Software;IT Engineering, École de technologie supérieure, Montreal, Canada 2School of Electrical \& Computer Engineering, National Technical University of Athens
Enhancing Online Learning by Integrating Biosensors and Multimodal Learning Analytics for Detecting and Predicting Student Behavior: A Review
Department of Computer Science Engineering, Universidad Autónoma de Madrid(马德里自治大学计算机科学工程系);Digital Futures Institute, Teachers College Columbia University(哥伦比亚大学教师学院数字未来研究所)
Online Prototype Alignment for Few-shot Policy Transfer
University of Science and Technology of China(中国科学技术大学);Institute of Computing Technology, CAS(中国科学院计算技术研究所);Cambricon Technologies(寒武纪科技);University of Chinese Academy of Sciences, China(中国科学院大学);Institute of Software Chinese Academy of Sciences(中国科学院软件研究所)
Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions
McGill University(麦吉尔大学);Quebec AI Institute(魁北克人工智能研究所);UC Berkeley(加州大学伯克利分校);Google Brain(谷歌大脑)
强化学习(RL)代理被广泛用于解决复杂的顺序决策任务,但仍然表现出难以推广到训练过程中看不到的场景。虽然先前的在线方法表明,使用奖励函数之外的额外信号可以在RL代理中产生更好的泛化能力,即使用自监督学习(SSL),但它们在离线RL设置中挣扎,即从静态数据集学习。我们发现,在RL的泛化在线算法的性能可能会受到阻碍,由于观察之间的相似性估计不良的离线设置。我们提出了一个新的理论动机的框架,称为广义相似性函数(GSF),它使用对比学习训练离线RL代理聚合观察的基础上,他们的预期未来行为的相似性,在那里我们量化这种相似性使用\emph{generalized value functions}。我们表明,GSF是一般的,足以恢复现有的SSL目标,同时也提高了zero-shot泛化性能的一个复杂的离线RL基准测试,离线Procgen。
Few-Shot Network Intrusion Detection Using Online Triplet Mining
Department of Electronics and Electrical Engineering, University of Strathclyde(斯特拉斯克莱德大学电子与电气工程系);Faculty of Computer and Information Sciences, Ain Shams University(爱思曼大学计算机与信息科学学院);Faculty of Electrical Engineering, Czech Technical University(捷克技术大学电气工程学院)
Updatable Siamese Tracker with Two-stage One-shot Learning
Changchun Institute of Optics Fine Mechanics and Physics Chinese Academy of Sciences(中国科学院长春光学精密机械与物理研究所);University of Chinese Academy of Sciences(中国科学院大学);Beijing Institute of Technology(北京理工大学)