Abstract:
We propose an efficient technique for performing data-driven optimal control of discrete-time systems. In particular, we show that log-sum-exp (LSE) neural networks, whic...Show MoreMetadata
Abstract:
We propose an efficient technique for performing data-driven optimal control of discrete-time systems. In particular, we show that log-sum-exp (LSE) neural networks, which are smooth and convex universal approximators of convex functions, can be efficiently used to approximate Q-factors arising from finite-horizon optimal control problems with continuous state space. The key advantage of these networks over classical approximation techniques is that they are convex and hence readily amenable to efficient optimization.
Published in: 2020 European Control Conference (ECC)
Date of Conference: 12-15 May 2020
Date Added to IEEE Xplore: 20 July 2020
ISBN Information: