TL;DR我们通过设计新的正则化技术,并将其与未经验证的未来成本预测相结合,实现了自适应于环境的 Non-stochastic Control 算法,这些算法通过考虑系统的内存具有新的数据自适应策略回归界限,并能在准确预测时收缩,即使全部失败时仍保持次线性。
Abstract
We tackle the problem of non-stochastic control with the aim of obtaining
algorithms that adapt to the controlled environment. Namely, we tailor the FTRL
framework to dynamical systems where the existence of a st