後知恵プランナー:実体指示追従のための閉ループ少数ショットプランナー
Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following
大規模言語モデルを用いた実体指示追従タスクにおいて、POMDPとして定式化し、適応モジュールと後知恵手法を組み合わせた閉ループプランナーを提案。少数ショット設定で従来の教師ありエージェントに匹敵または凌駕する性能を実現した。
著者: Yuxiao Yang, Shenao Zhang, Zhihan Liu, Huaxiu Yao, Zhaoran Wang
分類: cs.AI, cs.RO
原文アブストラクト
This work focuses on building a task planner for Embodied Instruction Following (EIF) using Large Language Models (LLMs). Previous works typically train a planner to imitate expert trajectories, treating this as a supervised task. While these methods achieve competitive performance, they often lack sufficient robustness. When a suboptimal action is taken, the planner may encounter an out-of-distribution state, which can lead to task failure. In contrast, we frame the task as a Partially Observable Markov Decision Process (POMDP) and aim to develop a robust planner under a few-shot assumption. Thus, we propose a closed-loop planner with an adaptation module and a novel hindsight method, aiming to use as much information as possible to assist the planner. Our experiments on the ALFRED dataset indicate that our planner achieves competitive performance under a few-shot assumption. For the first time, our few-shot agent's performance approaches and even surpasses that of the full-shot supervised agent.
