LIV：面向机器人控制的语言-图像表示与奖励
LIV: Language-Image Representations and Rewards for Robotic Control
AI总结：
本文提出 LIV 统一目标，从带文本标注的无动作视频中联合学习视觉-语言表示与奖励，并在仿真和真实机器人控制中验证其优于既有表示与奖励指定方法。
摘要：
我们提出了 Language-Image Value learning（LIV），这是一种统一目标，用于从带有文本标注且不含动作的视频中学习视觉-语言表示和奖励。LIV 目标利用双重强化学习与互信息对比学习之间的一种新颖联系，训练一个多模态表示，该表示隐式编码了一个通用价值函数，适用于以语言或图像目标指定的任务。我们使用 LIV 从 EpicKitchen 等大型人类视频数据集中预训练了首个以控制为中心的视觉-语言表示。仅给定语言或图像目标，预训练的 LIV 模型就能够为未见机器人或人类在未见环境中尝试该任务的视频中的每一帧分配稠密奖励。此外，当可以获得某些目标领域的特定数据时，同一目标还可用于微调并改进 LIV，甚至改进其他预训练表示，以服务于该领域中的机器人控制和奖励指定。在我们针对多个仿真和真实机器人环境的实验中，LIV 模型始终优于此前用于模仿学习的最佳输入状态表示，以及用于策略合成的奖励指定方法。我们的结果验证了在统一、紧凑的 LIV 框架内联合进行视觉-语言表示与奖励学习的优势。
英文摘要：
We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations. Exploiting a novel connection between dual reinforcement learning and mutual information contrastive learning, the LIV objective trains a multi-modal representation that implicitly encodes a universal value function for tasks specified as language or image goals. We use LIV to pre-train the first control-centric vision-language representation from large human video datasets such as EpicKitchen. Given only a language or image goal, the pre-trained LIV model can assign dense rewards to each frame in videos of unseen robots or humans attempting that task in unseen environments. Further, when some target domain-specific data is available, the same objective can be used to fine-tune and improve LIV and even other pre-trained representations for robotic control and reward specification in that domain. In our experiments on several simulated and real-world robot environments, LIV models consistently outperform the best prior input state representations for imitation learning, as well as reward specification methods for policy synthesis. Our results validate the advantages of joint vision-language representation and reward learning within the unified, compact LIV framework.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
