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 2201.08081cs.CL
收藏

LEMON:基于执行引导的预训练环境操纵

LEMON: Language-Based Environment Manipulation via Execution-Guided Pre-training

Harbin Institute of Technology(哈尔滨工业大学);Beihang University(北京航空航天大学);Microsoft Research Asia(微软亚洲研究院)

Qi Shi, Qian Liu, Bei Chen, Yu Zhang, Ting Liu, Jian-Guang Lou

摘要:

基于语义的环境操纵要求智能体按照自然语言指令操纵环境,由于环境空间巨大,这是一个挑战。为了应对这一挑战,最近的工作中提出了各种方法。尽管这些方法在预期的环境中工作良好,但它们很难跨环境进行推广。在这项工作中,我们提出了LEMON,基于语言的环境操作任务的一般框架。具体来说,我们首先指定一个任务不可知的方法,基于语言的环境操作任务,它可以处理各种环境使用相同的生成语言模型。然后,我们提出了一个执行引导的预训练策略注入先验知识的环境的语言模型与一个纯粹的合成预训练语料库。在Alchemy、Scene、Tangrams、ProPara和Recipes等任务上的实验结果证明了LEMON的有效性:它在其中四个任务上取得了新的最先进的结果,并且执行引导的预训练策略在所有实验任务上都带来了显着的改进。

英文摘要:

Language-based environment manipulation requires agents to manipulate the environment following natural language instructions, which is challenging due to the huge space of the environments. To address this challenge, various approaches have been proposed in recent work. Although these approaches work well for their intended environments, they are difficult to generalize across environments. In this work, we propose LEMON, a general framework for language-based environment manipulation tasks. Specifically, we first specify a task-agnostic approach for language-based environment manipulation tasks, which can deal with various environments using the same generative language model. Then we propose an execution-guided pre-training strategy to inject prior knowledge of environments to the language model with a pure synthetic pre-training corpus. Experimental results on tasks including Alchemy, Scene, Tangrams, ProPara and Recipes demonstrate the effectiveness of LEMON: it achieves new state-of-the-art results on four of the tasks, and the execution-guided pre-training strategy brings remarkable improvements on all experimental tasks.

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。

↑