规划、消除和跟踪 —— 语言模型是装备智能体的良师益友（英文版）

英文标题：Plan, Eliminate, and Track -- Language Models are Good Teachers for Embodied Agents中文摘要：使用大型语言模型的知识来简化控制问题，而不是直接解决它，作者提出了 Plan, Eliminate, and Track (PET) 框架，并在 AlfWorld 指令跟随基准测试中取得了显着的 15% 性能提升。英文摘要：Pre-trained large language models (LLMs) capture procedural knowledge aboutthe world. Recent work has leveraged LLM's ability to generate abstract plansto simplify challenging control tasks, either by action scoring, or actionmodeling (fine-tuning). However, the transformer architecture inheri