RoboCLIP：一次演示即可学习机器人策略
RoboCLIP: One Demonstration is Enough to Learn Robot Policies
AI总结：
RoboCLIP利用预训练视频-语言模型，通过单个视频或文本演示生成奖励，无需微调，使强化学习智能体在机器人操作任务上零样本性能提升2-3倍。
摘要：
奖励规范是强化学习中一个公认的难题，需要大量的专家监督来设计稳健的奖励函数。模仿学习（IL）方法试图通过利用专家演示来规避这些问题，但通常需要大量领域内的专家演示。受视频与语言模型（VLMs）领域进展的启发，我们提出了RoboCLIP，一种在线模仿学习方法，它使用单个演示（克服了大数据需求），形式为视频演示或任务文本描述，来生成奖励，无需手动设计奖励函数。此外，RoboCLIP还可以利用领域外演示，如人类解决任务的视频，用于奖励生成，从而避免了演示与部署领域必须相同的要求。RoboCLIP利用预训练的VLMs，无需任何微调即可进行奖励生成。使用RoboCLIP奖励训练的强化学习智能体在下游机器人操作任务上的零样本性能比竞争的模仿学习方法高出2-3倍，且仅使用一个视频或文本演示即可实现。
英文摘要：
Reward specification is a notoriously difficult problem in reinforcement learning, requiring extensive expert supervision to design robust reward functions. Imitation learning (IL) methods attempt to circumvent these problems by utilizing expert demonstrations but typically require a large number of in-domain expert demonstrations. Inspired by advances in the field of Video-and-Language Models (VLMs), we present RoboCLIP, an online imitation learning method that uses a single demonstration (overcoming the large data requirement) in the form of a video demonstration or a textual description of the task to generate rewards without manual reward function design. Additionally, RoboCLIP can also utilize out-of-domain demonstrations, like videos of humans solving the task for reward generation, circumventing the need to have the same demonstration and deployment domains. RoboCLIP utilizes pretrained VLMs without any finetuning for reward generation. Reinforcement learning agents trained with RoboCLIP rewards demonstrate 2-3 times higher zero-shot performance than competing imitation learning methods on downstream robot manipulation tasks, doing so using only one video/text demonstration.
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。
