Multitask LQG control via history-dependent lifting to LQR yields generalization bounds tied to bisimulation heterogeneity and reduces policy gradient variance proportionally to the number of training tasks.
Global convergence of policy gradient methods for the linear quadratic regulator
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
An evolutionary pruning algorithm co-designs actuators, sensors, and communication for distributed LQR control, achieving fast computation and over 50% better performance than naive pruning on a 98-state model with stability guarantees.
citing papers explorer
-
Multitask LQG Control: Performance and Generalization Bounds
Multitask LQG control via history-dependent lifting to LQR yields generalization bounds tied to bisimulation heterogeneity and reduces policy gradient variance proportionally to the number of training tasks.
-
An Evolutionary Algorithm for Actuator-Sensor-Communication Co-Design in Distributed Control
An evolutionary pruning algorithm co-designs actuators, sensors, and communication for distributed LQR control, achieving fast computation and over 50% better performance than naive pruning on a 98-state model with stability guarantees.