arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.06507cs.LGcs.AIcs.CVcs.RO
收藏

带视频的强化学习:将离线观察与交互相结合

Reinforcement Learning with Videos: Combining Offline Observations with Interaction

University of Pennsylvania(宾夕法尼亚大学);University of California Berkeley(加州大学伯克利分校);Stanford University(斯坦福大学)

Karl Schmeckpeper, Oleh Rybkin, Kostas Daniilidis, Sergey Levine, Chelsea Finn

摘要:

强化学习是机器人从经验中获取技能的强大框架,但通常需要大量的在线数据汇集。因此,很难收集机器人广泛推广所需的足够多样化的经验。另一方面,人类的视频是广泛而有趣的经验的现成来源。在本文中,我们考虑这样一个问题:我们可以直接对人类收集的经验进行强化学习吗?这个问题是特别困难的,因为这样的视频没有用动作注释,并且相对于机器人的实施例表现出显著的视觉域偏移。为了应对这些挑战,我们提出了一个视频强化学习(RLV)的框架。RLV使用人类收集的经验结合机器人收集的数据来学习策略和价值函数。在我们的实验中,我们发现RLV能够利用这些视频来学习具有挑战性的基于视觉的技能,其样本数量不到从头开始学习的RL方法的一半。

英文摘要:

Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is difficult to collect sufficiently diverse experiences that are needed for robots to generalize broadly. Videos of humans, on the other hand, are a readily available source of broad and interesting experiences. In this paper, we consider the question: can we perform reinforcement learning directly on experience collected by humans? This problem is particularly difficult, as such videos are not annotated with actions and exhibit substantial visual domain shift relative to the robot's embodiment. To address these challenges, we propose a framework for reinforcement learning with videos (RLV). RLV learns a policy and value function using experience collected by humans in combination with data collected by robots. In our experiments, we find that RLV is able to leverage such videos to learn challenging vision-based skills with less than half as many samples as RL methods that learn from scratch.

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。

↑