Policy Adaptation via Language Optimization: Decomposing Tasks for Few-Shot Imitation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Robot ManipulationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Words & Weights: Streamlining Multi-Turn Interactions via Co-Adaptation
Test-time policy adaptation for multi-turn interactions (T2PAM) is essential for aligning Large Language Models (LLMs) with dynamic user needs during inference time. However, existing paradigms commonly treat test-time a…
Test-time AdaptationPrompt EngineeringLLM Program Optimization via Retrieval Augmented Search
With the advent of large language models (LLMs), there has been a great deal of interest in applying them to solve difficult programming tasks. Recent work has demonstrated their potential at program optimization, a key …
RetrievalBiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptation
Parameter-efficient fine-tuning (PEFT) of large language models (LLMs) has gained considerable attention as a flexible and efficient way of adapting LLMs to downstream tasks. Among these methods, weighted decomposed low-…
Natural Language Understandingparameter-efficient fine-tuningText Generationtoken-classification+1Meta-Learning Integration in Hierarchical Reinforcement Learning for Advanced Task Complexity
Hierarchical Reinforcement Learning (HRL) effectively tackles complex tasks by decomposing them into structured policies. However, HRL agents often face challenges with efficient exploration and rapid adaptation. To addr…
Efficient ExplorationHierarchical Reinforcement LearningMeta-LearningAgentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
Vision-Language-Action (VLA) models have emerged as a promising paradigm for robotic manipulation by leveraging pre-trained vision-language representations. However, current VLA training methods suffer from two critical …