arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1709.10087cs.LGcs.AIcs.RO
收藏

用深度强化学习和演示学习复杂灵巧操作

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations

University of Washington(华盛顿大学);OpenAI;University of California Berkeley(加州大学伯克利分校);Istituto Italiano di Tecnologia(意大利理工学院)

Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta, Giulia Vezzani, John Schulman, Emanuel Todorov, Sergey Levine

摘要:

灵巧的多指手是非常通用的,并提供了一种通用的方式来执行以人为中心的环境中的许多任务。然而,有效地控制它们仍然具有挑战性,因为它们的高维度和大量的潜在接触。深度强化学习(DRL)提供了一种模型不可知的方法来控制复杂的动力系统,但尚未被证明可以扩展到高维灵巧操作。此外,由于样本效率低下,在物理系统上部署DRL仍然具有挑战性。因此,迄今为止,DRL在机器人领域的成功仅限于简单的机械手和任务。在这项工作中,我们表明,无模型DRL可以有效地扩展到复杂的操作任务与高维24自由度的手,并解决他们从头开始在模拟实验。此外,通过使用少量的人类演示,可以显着降低样本的复杂性,这使得学习的样本大小相当于几个小时的机器人经验。使用示威导致政策表现出非常自然的运动,而且令人惊讶的是,也更加强大。

英文摘要:

Dexterous multi-fingered hands are extremely versatile and provide a generic way to perform a multitude of tasks in human-centric environments. However, effectively controlling them remains challenging due to their high dimensionality and large number of potential contacts. Deep reinforcement learning (DRL) provides a model-agnostic approach to control complex dynamical systems, but has not been shown to scale to high-dimensional dexterous manipulation. Furthermore, deployment of DRL on physical systems remains challenging due to sample inefficiency. Consequently, the success of DRL in robotics has thus far been limited to simpler manipulators and tasks. In this work, we show that model-free DRL can effectively scale up to complex manipulation tasks with a high-dimensional 24-DoF hand, and solve them from scratch in simulated experiments. Furthermore, with the use of a small number of human demonstrations, the sample complexity can be significantly reduced, which enables learning with sample sizes equivalent to a few hours of robot experience. The use of demonstrations result in policies that exhibit very natural movements and, surprisingly, are also substantially more robust.

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。

↑