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 propose a unified approach to 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 and ProPara demonstrate the effectiveness of LEMON: it achieves new state-of-the-art results on Alchemy, Scene and ProPara, and the execution-guided pre-training strategy brings remarkable improvements on all experimental tasks.

本文提出了LEMON框架，通过使用生成式语言模型和执行指导的预训练策略，实现面向各种环境的语言操作任务，并在Alchemy、Scene、Tangrams、ProPara和Recipes任务上取得新的最佳效果。

LEMON：基于语言的环境操作与执行引导的预训练