Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation

TL;DR

This paper introduces PALO, a method that leverages vision-language models to decompose tasks and enable rapid few-shot adaptation of robot policies to new, complex tasks without extensive retraining.

Contribution

The paper presents a novel approach combining task decomposition with language optimization for effective few-shot adaptation in robot manipulation.

Findings

PALO outperforms existing policies on complex real-world tasks.

It enables rapid adaptation without large fine-tuning datasets.

Successfully handles long-horizon, multi-step tasks in real environments.

Abstract

Learned language-conditioned robot policies often struggle to effectively adapt to new real-world tasks even when pre-trained across a diverse set of instructions. We propose a novel approach for few-shot adaptation to unseen tasks that exploits the semantic understanding of task decomposition provided by vision-language models (VLMs). Our method, Policy Adaptation via Language Optimization (PALO), combines a handful of demonstrations of a task with proposed language decompositions sampled from a VLM to quickly enable rapid nonparametric adaptation, avoiding the need for a larger fine-tuning dataset. We evaluate PALO on extensive real-world experiments consisting of challenging unseen, long-horizon robot manipulation tasks. We find that PALO is able of consistently complete long-horizon, multi-tier tasks in the real world, outperforming state of the art pre-trained generalist policies, and methods that have access to the same demonstrations.