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.
Convergence and sample complexity of policy gradient methods for stabilizing linear systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
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.