Learning Goal-Oriented Hierarchical Tasks from Situated Interactive Instruction
Learning Goal-Oriented Hierarchical Tasks from Situated Interactive Instruction
复制标题
从情境互动教学中学习目标导向的分层任务
DOI：
10.1609/aaai.v28i1.8756
复制
发表时间：
2014
期刊：
影响因子：
--
通讯作者：
J. Laird
中科院分区：
文献类型：
--
作者：
Shiwali Mohan;J. Laird
我们的研究旨在构建能够通过与人类用户交互来扩展知识的交互式机器人和智能体。在本文中，我们专注于从情境交互指令中学习以目标为导向的任务。学习新任务的结构以及如何执行它们是一个具有挑战性的计算问题，要求智能体获取包括目标定义和分层控制信息在内的各种知识。我们将新任务的获取视为一个基于解释的学习（EBL）问题，并为机器人智能体提出了一种EBL的交互式学习变体。我们表明，我们的方法可以利用情境指令中的信息以及领域知识，在多个任务上展示出快速的泛化能力。所获取的知识能在结构相似的任务之间迁移。最后，我们表明我们的方法将智能体驱动的探索与用于混合主动学习的指令无缝结合。
Our research aims at building interactive robots and agents that can expand their knowledge by interacting with human users. In this paper, we focus on learning goal-oriented tasks from situated interactive instructions. Learning the structure of novel tasks and how to execute them is a challenging computational problem requiring the agent to acquire a variety of knowledge including goal definitions and hierarchical control information. We frame acquisition of novel tasks as an explanation-based learning (EBL) problem and propose an interactive learning variant of EBL for a robotic agent. We show that our approach can exploit information in situated instructions along with the domain knowledge to demonstrate fast generalization on several tasks. The knowledge acquired transfers across structurally similar tasks. Finally, we show that our approach seamlessly combines agent-driven exploration with instructions for mixed-initiative learning.