Online Control
A class of sequential decision-making frameworks in which the decision maker adjusts strategies step by step based on historical feedback without prior knowledge of the future environment, emphasizing learning while making decisions.
Timeline (last 90 days)
AMTP formulates horizon selection as an online control problem, learning the optimal horizon online through verification feedback.
Simulation can characterize stochastic processes such as random memory waiting times and entanglement generation probabilities, providing a more accurate fidelity distribution, but its computational cost is high and may fail to meet the real-time requirements of online control.
Lightweight learned surrogate models learn the simulator's input-output mapping through offline training and perform fast inference online, supporting online control at lower runtime cost.
All Facts (3)
AMTP formulates horizon selection as an online control problem, learning the optimal horizon online through verification feedback.
50%UnverifiedSimulation can characterize stochastic processes such as random memory waiting times and entanglement generation probabilities, providing a more accurate fidelity distribution, but its computational cost is high and may fail to meet the real-time requirements of online control.
50%UnverifiedLightweight learned surrogate models learn the simulator's input-output mapping through offline training and perform fast inference online, supporting online control at lower runtime cost.
50%