Promises of Deep Kernel Learning for Control Synthesis

arXiv:2309.06569v2 Announce Type: replace-cross
Abstract: Deep Kernel Learning (DKL) combines the representational power of neural networks with the uncertainty quantification of Gaussian Processes. Hence, it is potentially a promising tool to learn and control complex dynamical systems. In this work, we develop a scalable abstraction-based framework that enables the use of DKL for control synthesis of stochastic dynamical systems against complex specifications. Specifically, we consider temporal logic specifications and create an end-to-end framework that uses DKL to learn an unknown …

abstract abstraction arxiv control cs.lg cs.sy eess.sy framework gaussian processes kernel learn networks neural networks power processes quantification scalable synthesis systems tool type uncertainty work