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

arXiv: https://arxiv.org/abs/2412.19562 · HTML: https://mlsanity.com/paper/2412.19562/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 1 of its 39 references that are in the map.
- First posted on arXiv 27 Dec 2024.

## Builds on (most cited first, 1 of 1)

- [Learning to Reach Goals via Iterated Supervised Learning](https://mlsanity.com/paper/1912.06088/) (2019)

## Built on by (most cited first, 1 of 1)

- [World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning](https://mlsanity.com/paper/2503.10480/) (2025)

## Abstract (arXiv)

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.