Regret Analysis of Learning-Based MPC with Partially-Unknown Cost Function
Dogan, Ilgin, Shen, Zuo-Jun Max, Aswani, Anil
–arXiv.org Artificial Intelligence
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.
arXiv.org Artificial Intelligence
Jan-27-2023
- Country:
- North America > United States (0.28)
- Asia (0.28)
- Genre:
- Research Report (0.82)
- Industry:
- Energy > Oil & Gas > Downstream (0.82)
- Technology: