一句话：提出 Adaptation²，主张用强化学习让规约学习器在运行时自适应配置，以支撑可保证的自适应系统。
规约学习与控制器综合有望让控制系统在运行时具备可保证的自适应能力。前者可从运行环境中观察到的违反轨迹自动更新规约，后者据此生成满足规约的实现。然而规约学习由通用 AI 系统实现，这类系统高度可配置，配置选择显著影响效果，且参数与自适应任务缺乏清晰语义关联，现有方法需要领域专家在设计时为每个应用领域设定配置。本文主张，要使保证型控制系统在运行时高效有效地适应，其底层学习系统也必须具备运行时可自适应的学习策略；作者用强化学习计算领域相关策略，给出概念验证。
Specification learning and controller synthesis are two methods that promise to provide control systems with assured adaptive capabilities at run-time. Specification learning can automatically update specifications in light of violation traces observed within the operational environment. Controller synthesis can then automatically generate implementations that are guaranteed to satisfy these specifications in every environment.Specification learning is implemented using general-purpose AI systems. These systems are highly configurable, and the configuration choice heavily affects the effectiveness. Setting configuration parameters is far from obvious as they bear no clear semantic relation with the adaptation task. State of the art requires configurations to be set by domain experts at design time for each application domain.In this paper, we argue that to create assured control systems that can effectively and efficiently adapt at run-time, the learning systems upon which they are built must also have adaptive learning strategies for determining configurations at runtime. We demonstrate this idea with a proof-of-concept that computes domain-dependent policies using reinforcement learning.
DOI 原文 ·
@inproceedings{paperbot6525,
title = {Adaptation<sup>2</sup>: Adapting Specification Learners in Assured Adaptive Systems},
author = {Dalal Alrajeh and Patrick Benjamin and Sebastian Uchitel},
booktitle = {ASE},
year = {2021},
doi = {10.1109/ase51524.2021.9678919}
}