paper-with-me

Papers

LLMs for Generalizable Language-Conditioned Policy Learning under Minimal Data Requirements

2024-12-09 · Thomas Pouplin, Katarzyna Kobalczyk, Hao Sun, Mihaela van der Schaar

To develop autonomous agents capable of executing complex, multi-step decision-making tasks as specified by humans in natural language, existing reinforcement learning approaches typically require expensive labeled datasets or access to real-time experimentation. Moreover, conventional methods often face difficulties in generalizing to unseen goals and states, thereby limiting their practical applicability. This paper presents TEDUO, a novel training pipeline for offline language-conditioned policy learning. TEDUO operates on easy-to-obtain, unlabeled datasets and is suited for the so-called in-the-wild evaluation, wherein the agent encounters previously unseen goals and states. To address the challenges posed by such data and evaluation settings, our method leverages the prior knowledge and instruction-following capabilities of large language models (LLMs) to enhance the fidelity of pre-collected offline data and enable flexible generalization to new goals and states. Empirical results demonstrate that the dual role of LLMs in our framework-as data enhancers and generalizers-facilitates both effective and data-efficient learning of generalizable language-conditioned policies.

📄 PDF Abstract BibTeX arXiv:2412.06877

Code (0)

등록된 구현이 없습니다.

Tasks

Decision MakingInstruction Following

Similar Papers 제목 키워드 기반

Large Language Models as Generalizable Policies for Embodied Tasks

2023-10-26 · Andrew Szot, Max Schwarzer, Harsh Agrawal, Bogdan Mazoure 외

We show that large language models (LLMs) can be adapted to be generalizable policies for embodied visual tasks. Our approach, called Large LAnguage model Reinforcement Learning Policy (LLaRP), adapts a pre-trained froze…

Language ModelingLanguage ModellingLarge Language Modelreinforcement-learning+1

PlanPO: Group Planning-Aware Policy Optimization for Multi-Turn Agentic LLMs

2026-08-18 · Dayang Liang, Liyuan He, Xuan Feng, Shuxin Li 외 arxiv

Group-relative policy optimization has emerged as a key paradigm for training agentic large language models (LLMs) on multi-turn interactive tasks. However, most existing variants fail to distinguish advantages among suc…

IntPro: A Proxy Agent for Context-Aware Intent Understanding via Retrieval-conditioned Inference

2026-02-10 · Guanming Liu, Meng Wu, Peng Zhang, Yu Zhang 외 arxiv

Large language models (LLMs) have become integral to modern Human-AI collaboration workflows, where accurately understanding user intent serves as a crucial step for generating satisfactory responses. Context-aware inten…

NVSPolicy: Adaptive Novel-View Synthesis for Generalizable Language-Conditioned Policy Learning

2025-05-15 · Le Shi, Yifei Shi, Xin Xu, Tenglong Liu 외

Recent advances in deep generative models demonstrate unprecedented zero-shot generalization capabilities, offering great potential for robot manipulation in unstructured environments. Given a partial observation of a sc…

Novel View SynthesisRobot ManipulationZero-shot Generalization

Towards Generalizable Vision-Language Robotic Manipulation: A Benchmark and LLM-guided 3D Policy

2024-10-02 · Ricardo Garcia, ShiZhe Chen, Cordelia Schmid

Generalizing language-conditioned robotic policies to new tasks remains a significant challenge, hampered by the lack of suitable simulation benchmarks. In this paper, we address this gap by introducing GemBench, a novel…

Motion PlanningRobot ManipulationRobot Manipulation GeneralizationTask Planning