arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.03552cs.RO
收藏

平衡态下主动学习的遍历测度

An Ergodic Measure for Active Learning From Equilibrium

Northwestern University(西北大学)

Ian Abraham, Ahalya Prabhakar, Todd D. Murphey

摘要:

本文开发了KL-遍历探索从平衡($\text{KL-E}^3$),机器人系统的方法,以整合稳定性,积极产生信息的测量,通过遍历探索。遍历探索使机器人系统能够从全局信息空间分布中间接采样,避免局部最优,并且不需要针对机器人动力学评估分布的导数。使用混合系统理论,我们推导出一个控制器,允许机器人利用平衡策略(即,解决任务的策略),同时允许机器人使用可以扩展到高维状态的遍历度量来探索和生成信息数据。我们表明,我们的方法是能够保持李雅普诺夫吸引力相对于平衡任务,同时积极生成数据的学习任务,如贝叶斯优化,模型学习,政策外强化学习。在每个例子中,我们表明,我们提出的方法是能够生成一个信息丰富的数据分布,同时合成平滑的控制信号。我们说明这些例子,使用模拟系统,并提供简化我们的方法在机器人系统中的实时在线学习。

英文摘要:

This paper develops KL-Ergodic Exploration from Equilibrium ($\text{KL-E}^3$), a method for robotic systems to integrate stability into actively generating informative measurements through ergodic exploration. Ergodic exploration enables robotic systems to indirectly sample from informative spatial distributions globally, avoiding local optima, and without the need to evaluate the derivatives of the distribution against the robot dynamics. Using hybrid systems theory, we derive a controller that allows a robot to exploit equilibrium policies (i.e., policies that solve a task) while allowing the robot to explore and generate informative data using an ergodic measure that can extend to high-dimensional states. We show that our method is able to maintain Lyapunov attractiveness with respect to the equilibrium task while actively generating data for learning tasks such, as Bayesian optimization, model learning, and off-policy reinforcement learning. In each example, we show that our proposed method is capable of generating an informative distribution of data while synthesizing smooth control signals. We illustrate these examples using simulated systems and provide simplification of our method for real-time online learning in robotic systems.

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。

↑