arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2208.09554cs.AI
收藏

整合多样知识源用于新任务的在线一次性学习

Integrating Diverse Knowledge Sources for Online One-shot Learning of Novel Tasks

IQM Research Institute(IQM研究院)

James R. Kirk, Robert E. Wray, Peter Lindes, John E. Laird

AI总结:

本文研究自主智能体整合多种知识源(环境交互、任务执行、自然语言指令和GPT-3响应)以在线一次性学习新任务,实验表明该方法减少人类反馈并提升学习效果。

摘要:

自主智能体能够利用多种潜在的任务知识来源,然而当前的方法通常只关注其中一两种。在此,我们研究了利用多样知识源来让模拟办公移动机器人在线、一次性学习新任务所面临的挑战和影响。所构建的智能体基于Soar认知架构开发,使用了以下领域和任务知识来源:与环境交互、任务执行和搜索知识、人类自然语言指令,以及从大型语言模型(GPT-3)检索的响应。我们探讨了这些知识来源的不同贡献,并评估了不同组合在正确学习任务知识和人类工作量方面的性能。结果表明,智能体在线整合多样知识源整体上提升了一次性任务学习,减少了快速可靠任务学习所需的人类反馈。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑