arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.03427cs.AIcs.CL
收藏

基于统一Transformers和自我监控的语言指令分层任务学习

Hierarchical Task Learning from Language Instructions with Unified Transformers and Self-Monitoring

University of Michigan(密歇根大学)

Yichi Zhang, Joyce Chai

摘要:

尽管最近取得了进展,但通过语言指令学习新任务仍然是一个极具挑战性的问题。在任务学习的ALFRED基准测试中,已发布的最先进系统在看不见的环境中仅实现了不到10%的任务成功率,而人类的成功率超过90%。为了解决这个问题,本文仔细研究了任务学习。与广泛应用的端到端架构不同,我们将任务学习分解为三个子问题:子目标规划,场景导航和对象操作;并开发了一个模型HiTUT(代表通过统一Transformers的分层任务),该模型以统一的方式解决每个子问题,以学习分层任务结构。在ALFRED基准测试中,HiTUT取得了最好的性能,具有显着更高的泛化能力。在未知环境中,HiTUT的成功率比以前的技术水平提高了160%以上。任务结构的显式表示也使人们能够深入了解问题的性质和智能体的能力,为未来的基准开发和评估提供了洞察力。

英文摘要:

Despite recent progress, learning new tasks through language instructions remains an extremely challenging problem. On the ALFRED benchmark for task learning, the published state-of-the-art system only achieves a task success rate of less than 10% in an unseen environment, compared to the human performance of over 90%. To address this issue, this paper takes a closer look at task learning. In a departure from a widely applied end-to-end architecture, we decomposed task learning into three sub-problems: sub-goal planning, scene navigation, and object manipulation; and developed a model HiTUT (stands for Hierarchical Tasks via Unified Transformers) that addresses each sub-problem in a unified manner to learn a hierarchical task structure. On the ALFRED benchmark, HiTUT has achieved the best performance with a remarkably higher generalization ability. In the unseen environment, HiTUT achieves over 160% performance gain in success rate compared to the previous state of the art. The explicit representation of task structures also enables an in-depth understanding of the nature of the problem and the ability of the agent, which provides insight for future benchmark development and evaluation.

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。

↑