The paper claims entropy regularization forces the optimal LQ feedback policy to be Gaussian and uses that to solve a mean-variance asset-liability problem, but the proof of the main theorem contains a correlation error that invalidates the general claim.
Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function
1 Pith paper cite this work. Polarity classification is still indexing.
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
citation-polarity summary
fields
stat.ML 1years
2024 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Reinforcement Learning for a Discrete-Time Linear-Quadratic Control Problem with an Application
The paper claims entropy regularization forces the optimal LQ feedback policy to be Gaussian and uses that to solve a mean-variance asset-liability problem, but the proof of the main theorem contains a correlation error that invalidates the general claim.