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 2102.12585cs.LGmath.OC
收藏

面向安全连续任务的强化学习

Towards Safe Continuing Task Reinforcement Learning

Massachusetts Institute of Technology(麻省理工学院);University of Pennsylvania(宾夕法尼亚大学);Rensselaer Polytechnic Institute(伦斯勒理工学院)

Miguel Calvo-Fullana, Luiz F. O. Chamon, Santiago Paternain

摘要:

安全性是物理系统控制器设计的关键特征。在设计控制策略时,已经提出了几种方法来保证这方面的自主性,如鲁棒控制器或控制障碍函数。然而,这些解决方案强烈依赖于设计者可用的系统模型。作为一个平行的发展,强化学习提供了模型不可知的控制解决方案,但在一般情况下,它缺乏安全所需的理论保证。最近的进展表明,在温和的条件下,控制策略可以通过强化学习来学习,通过将这些要求作为优化问题的约束来保证控制策略是安全的。然而,要从学习安全转移到学习安全,需要克服两个障碍:(i)必须能够在不必重新初始化系统的情况下学习策略;以及(ii)系统的推出本身需要安全。在本文中,我们解决了第一个问题,提出了一种算法,能够在连续的任务设置,而不需要重新启动。我们评估我们的方法在一个数值例子中,这表明所提出的方法在学习安全的政策,通过安全的探索能力。

英文摘要:

Safety is a critical feature of controller design for physical systems. When designing control policies, several approaches to guarantee this aspect of autonomy have been proposed, such as robust controllers or control barrier functions. However, these solutions strongly rely on the model of the system being available to the designer. As a parallel development, reinforcement learning provides model-agnostic control solutions but in general, it lacks the theoretical guarantees required for safety. Recent advances show that under mild conditions, control policies can be learned via reinforcement learning, which can be guaranteed to be safe by imposing these requirements as constraints of an optimization problem. However, to transfer from learning safety to learning safely, there are two hurdles that need to be overcome: (i) it has to be possible to learn the policy without having to re-initialize the system; and (ii) the rollouts of the system need to be in themselves safe. In this paper, we tackle the first issue, proposing an algorithm capable of operating in the continuing task setting without the need of restarts. We evaluate our approach in a numerical example, which shows the capabilities of the proposed approach in learning safe policies via safe exploration.

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。

↑