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 1502.02860stat.MLcs.LGcs.ROcs.SYeess.SY
收藏

高斯过程在机器人和控制中的数据高效学习

Gaussian Processes for Data-Efficient Learning in Robotics and Control

TU Darmstadt(达姆施塔特工业大学);University of Washington(华盛顿大学);University of Cambridge(剑桥大学)

Marc Peter Deisenroth, Dieter Fox, Carl Edward Rasmussen

AI总结:

本文提出基于高斯过程的非参数转移模型,通过提取更多数据信息加速学习,减少模型误差影响,实现高效自主学习。

摘要:

自主学习在控制和机器人领域已持续十多年,数据驱动学习可减少工程知识需求。然而,自主强化学习通常需要大量系统交互,这在实际系统中(如机器人)不现实。本文提出通过高斯过程转移模型提取更多数据信息,显式纳入模型不确定性以减少误差影响,相比现有RL方法,模型基于策略搜索方法实现了前所未有的学习速度,并在真实机器人和控制任务中展示了应用价值。

英文摘要:

Autonomous learning has been a promising direction in control and robotics for more than a decade since data-driven learning allows to reduce the amount of engineering knowledge, which is otherwise required. However, autonomous reinforcement learning (RL) approaches typically require many interactions with the system to learn controllers, which is a practical limitation in real systems, such as robots, where many interactions can be impractical and time consuming. To address this problem, current learning approaches typically require task-specific knowledge in form of expert demonstrations, realistic simulators, pre-shaped policies, or specific knowledge about the underlying dynamics. In this article, we follow a different approach and speed up learning by extracting more information from data. In particular, we learn a probabilistic, non-parametric Gaussian process transition model of the system. By explicitly incorporating model uncertainty into long-term planning and controller learning our approach reduces the effects of model errors, a key problem in model-based learning. Compared to state-of-the art RL our model-based policy search method achieves an unprecedented speed of learning. We demonstrate its applicability to autonomous learning in real robot and control tasks.

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。

↑