Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yuxiao, Zhang, Shenao, Liu, Zhihan, Yao, Huaxiu, Wang, Zhaoran
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929648892379136
author Yang, Yuxiao
Zhang, Shenao
Liu, Zhihan
Yao, Huaxiu
Wang, Zhaoran
author_facet Yang, Yuxiao
Zhang, Shenao
Liu, Zhihan
Yao, Huaxiu
Wang, Zhaoran
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19562
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following
Yang, Yuxiao
Zhang, Shenao
Liu, Zhihan
Yao, Huaxiu
Wang, Zhaoran
Artificial Intelligence
Robotics
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.
title Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following
topic Artificial Intelligence
Robotics
url https://arxiv.org/abs/2412.19562