Real-World Offline Reinforcement Learning from Vision Language Model Feedback

TL;DR

This paper introduces a system that automatically generates reward labels from vision-language feedback for offline reinforcement learning, enabling effective policy learning in real-world robotic tasks without manual reward annotation.

Contribution

It presents a novel approach combining vision-language models with offline RL to automatically label rewards, facilitating policy learning from unlabeled, sub-optimal datasets.

Findings

Successfully applied to a real-world robot dressing task

Outperforms behavior cloning and inverse RL baselines

Effective in simulation with rigid and deformable objects

Abstract

Offline reinforcement learning can enable policy learning from pre-collected, sub-optimal datasets without online interactions. This makes it ideal for real-world robots and safety-critical scenarios, where collecting online data or expert demonstrations is slow, costly, and risky. However, most existing offline RL works assume the dataset is already labeled with the task rewards, a process that often requires significant human effort, especially when ground-truth states are hard to ascertain (e.g., in the real-world). In this paper, we build on prior work, specifically RL-VLM-F, and propose a novel system that automatically generates reward labels for offline datasets using preference feedback from a vision-language model and a text description of the task. Our method then learns a policy using offline RL with the reward-labeled dataset. We demonstrate the system's applicability to a complex real-world robot-assisted dressing task, where we first learn a reward function using a vision-language model on a sub-optimal offline dataset, and then we use the learned reward to employ Implicit Q learning to develop an effective dressing policy. Our method also performs well in simulation tasks involving the manipulation of rigid and deformable objects, and significantly outperform baselines such as behavior cloning and inverse RL. In summary, we propose a new system that enables automatic reward labeling and policy learning from unlabeled, sub-optimal offline datasets.