Learning Personalized Optimal Control for Repeatedly Operated Systems
This work addresses control optimization for systems with unknown stochastic parameters, but it appears incremental as it builds on existing online learning frameworks without claiming major breakthroughs.
The paper tackles the problem of online learning of optimal control for repeatedly operated systems with parametric uncertainty, where an agent personalizes control inputs to a plant based on stochastic parameters, and demonstrates effectiveness on a simulated system.
We consider the problem of online learning of optimal control for repeatedly operated systems in the presence of parametric uncertainty. During each round of operation, environment selects system parameters according to a fixed but unknown probability distribution. These parameters govern the dynamics of a plant. An agent chooses a control input to the plant and is then revealed the cost of the choice. In this setting, we design an agent that personalizes the control input to this plant taking into account the stochasticity involved. We demonstrate the effectiveness of our approach on a simulated system.