基于修正学习的协同系统辨识
Cooperative System Identification via Correctional Learning
摘要：
我们认为一个合作的系统辨识方案中，一个专家代理（教师）知道一个正确的，或至少是一个好的，系统的模型，旨在帮助学习者代理（学生），但不能直接将其知识的学生。例如，教师对系统的知识可能是抽象的，或者教师和学生可能采用不同的模型类，这使得教师的参数对学生没有信息。在本文中，我们提出了纠正学习作为上述问题的一种方法：假设，为了帮助学生，教师可以截取从系统收集的意见，并修改它们，以最大限度地提高信息量的学生收到有关系统。我们制定了一个通用的解决方案作为一个优化问题，这对于一个多项式系统实例本身作为一个整数规划。此外，我们获得有限样本的结果，从教师的帮助下的结果（如测量的方差估计的减少）为一个二项式系统的改进。
英文摘要：
We consider a cooperative system identification scenario in which an expert agent (teacher) knows a correct, or at least a good, model of the system and aims to assist a learner-agent (student), but cannot directly transfer its knowledge to the student. For example, the teacher's knowledge of the system might be abstract or the teacher and student might be employing different model classes, which renders the teacher's parameters uninformative to the student. In this paper, we propose correctional learning as an approach to the above problem: Suppose that in order to assist the student, the teacher can intercept the observations collected from the system and modify them to maximize the amount of information the student receives about the system. We formulate a general solution as an optimization problem, which for a multinomial system instantiates itself as an integer program. Furthermore, we obtain finite-sample results on the improvement that the assistance from the teacher results in (as measured by the reduction in the variance of the estimator) for a binomial system.
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。
