We investigate the challenge of task planning for multi-task embodied agents in open-world environments. Two main difficulties are identified: 1) executing plans in an open-world environment (e.g., Minecraft) necessitates accurate and multi-step reasoning due to the long-term nature of tasks, and 2) as vanilla planners do not consider how easy the current agent can achieve a given sub-task when ordering parallel sub-goals within a complicated plan, the resulting plan could be inefficient or even infeasible. To this end, we propose "$\underline{D}$escribe, $\underline{E}$xplain, $\underline{P}$lan and $\underline{S}$elect" ($\textbf{DEPS}$), an interactive planning approach based on Large Language Models (LLMs). DEPS facilitates better error correction on initial LLM-generated $\textit{plan}$ by integrating $\textit{description}$ of the plan execution process and providing self-$\textit{explanation}$ of feedback when encountering failures during the extended planning phases. Furthermore, it includes a goal $\textit{selector}$, which is a trainable module that ranks parallel candidate sub-goals based on the estimated steps of completion, consequently refining the initial plan. Our experiments mark the milestone of the first zero-shot multi-task agent that can robustly accomplish 70+ Minecraft tasks and nearly double the overall performances. Further testing reveals our method's general effectiveness in popularly adopted non-open-ended domains as well (i.e., ALFWorld and tabletop manipulation). The ablation and exploratory studies detail how our design beats the counterparts and provide a promising update on the $\texttt{ObtainDiamond}$ grand challenge with our approach. The code is released at https://github.com/CraftJarvis/MC-Planner.

翻译：我们研究了开放世界环境下多任务具身智能体的任务规划挑战。主要存在两个难点：1）在开放世界环境（如Minecraft）中执行规划需要进行精确的多步推理，这是由于任务的长期性；2）当基础规划器在复杂计划中排序并行子目标时，未考虑当前智能体完成给定子任务的难易程度，导致生成的计划可能低效甚至不可行。为此，我们提出"描述、解释、规划与选择"（DEPS）方法，这是一种基于大语言模型（LLMs）的交互式规划方法。DEPS通过整合规划执行过程的描述，并在扩展规划阶段遇失败时提供反馈的自我解释，促进对LLM初始生成计划的纠错。此外，它包含一个可训练的目标选择器，该模块根据预估完成步数对并行候选子目标进行排序，从而优化初始计划。我们的实验标志着首个零样本多任务智能体的里程碑——该智能体可稳健完成70余项Minecraft任务，并实现总体性能近乎翻倍。进一步测试表明，该方法在广泛采用的非开放领域（如ALFWorld和桌面操作）同样具有普适有效性。消融与探索性研究详细揭示了我们的设计如何优于对照方法，并基于我们的方法为ObtainDiamond重大挑战提供了有前景的进展。相关代码已开源在https://github.com/CraftJarvis/MC-Planner。