Promises of Deep Kernel Learning for Control Synthesis

TL;DR

This paper introduces a scalable framework using Deep Kernel Learning to learn, abstract, and synthesize control policies for complex stochastic systems with formal guarantees, outperforming existing methods.

Contribution

It develops a novel end-to-end approach combining DKL with formal abstraction for control synthesis of stochastic systems with correctness guarantees.

Findings

Effective control synthesis on complex benchmarks

Outperforms state-of-the-art methods

Accurate learning and efficient abstraction architecture

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 system from data and formally abstracts the DKL model into an Interval Markov Decision Process (IMDP) to perform control synthesis with correctness guarantees. Furthermore, we identify a deep architecture that enables accurate learning and efficient abstraction computation. The effectiveness of our approach is illustrated on various benchmarks, including a 5-D nonlinear stochastic system, showing how control synthesis with DKL can substantially outperform state-of-the-art competitive methods.