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.
Policy gradient for LQR with domain randomization,
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.