Characterizing an Analogical Concept Memory for Newellian Cognitive Architectures

arxiv(2020)

引用 0|浏览13
暂无评分
摘要
We propose a new long-term declarative memory for Soar that leverages the computational models of analogical reasoning and generalization. We situate our research in interactive task learning (ITL) and embodied language processing (ELP). We demonstrate that the learning methods implemented in the proposed memory can quickly learn a diverse types of novel concepts that are useful in task execution. Our approach has been instantiated in an implemented hybrid AI system AILEEN and evaluated on a simulated robotic domain.
更多
查看译文
关键词
analogical concept memory
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要