Pith. sign in

Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

The exploration/exploitation trade-off is an inherent challenge in data-driven adaptive control. Though this trade-off has been studied for multi-armed bandits (MAB's) and reinforcement learning for linear systems; it is less well-studied for learning-based control of nonlinear systems. A significant theoretical challenge in the nonlinear setting is that there is no explicit characterization of an optimal controller for a given set of cost and system parameters. We propose the use of a finite-horizon oracle controller with full knowledge of parameters as a reasonable surrogate to optimal controller. This allows us to develop policies in the context of learning-based MPC and MAB's and conduct a control-theoretic analysis using techniques from MPC- and optimization-theory to show these policies achieve low regret with respect to this finite-horizon oracle. Our simulations exhibit the low regret of our policy on a heating, ventilation, and air-conditioning model with partially-unknown cost function.

citation-role summary

background 1

citation-polarity summary

fields

stat.ML 1

years

2024 1

verdicts

REJECT 1

roles

background 1

polarities

background 1

representative citing papers

citing papers explorer

Showing 1 of 1 citing paper.