扩散增强智能体：高效探索与迁移学习的框架

Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning

July 30, 2024

作者: Norman Di Palo, Leonard Hasenclever, Jan Humplik, Arunkumar Byravan

cs.AI

摘要

我们介绍了扩散增强代理（DAAG），这是一个新颖的框架，利用大型语言模型、视觉语言模型和扩散模型来提高具身体代理的强化学习中的样本效率和迁移学习。DAAG通过利用扩散模型对视频进行转换，以一种时间和几何一致的方式重新标记代理的过去经验，以使其与目标指令对齐，这一技术称为事后经验增强。一个大型语言模型协调这一自主过程，无需人类监督，非常适合终身学习场景。该框架减少了需要标记奖励数据的量，用于1）微调作为奖励检测器的视觉语言模型，以及2）训练RL代理执行新任务。我们展示了DAAG在涉及操作和导航的模拟机器人环境中的样本效率增益。我们的结果表明，DAAG改善了奖励检测器的学习、迁移过去经验和获取新任务的能力，这是开发高效终身学习代理的关键能力。我们的网站提供了补充材料和可视化内容：https://sites.google.com/view/diffusion-augmented-agents/

English

We introduce Diffusion Augmented Agents (DAAG), a novel framework that leverages large language models, vision language models, and diffusion models to improve sample efficiency and transfer learning in reinforcement learning for embodied agents. DAAG hindsight relabels the agent's past experience by using diffusion models to transform videos in a temporally and geometrically consistent way to align with target instructions with a technique we call Hindsight Experience Augmentation. A large language model orchestrates this autonomous process without requiring human supervision, making it well-suited for lifelong learning scenarios. The framework reduces the amount of reward-labeled data needed to 1) finetune a vision language model that acts as a reward detector, and 2) train RL agents on new tasks. We demonstrate the sample efficiency gains of DAAG in simulated robotics environments involving manipulation and navigation. Our results show that DAAG improves learning of reward detectors, transferring past experience, and acquiring new tasks - key abilities for developing efficient lifelong learning agents. Supplementary material and visualizations are available on our website https://sites.google.com/view/diffusion-augmented-agents/