Derives an ε-local minimax excess-cost lower bound for learning LQG controllers from offline trajectories of a linear exploration policy, expressed via the Hessian of the LQG cost and inverse Fisher information, and instantiates it on fragile robust-control examples.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
eess.SY 3years
2026 3verdicts
UNVERDICTED 3representative citing papers
Leader-following consensus under disturbances is solved by modeling it as a coalitional zero-sum game that yields an H∞ law implementable distributively through GARE decomposition and dynamic average consensus.
An online algorithm for zero-sum LQ games with unknown dynamics combines model estimation and surrogate selection to achieve regret bounds on policy convergence.
citing papers explorer
-
The Fragility of Learning LQG Controllers
Derives an ε-local minimax excess-cost lower bound for learning LQG controllers from offline trajectories of a linear exploration policy, expressed via the Hessian of the LQG cost and inverse Fisher information, and instantiates it on fragile robust-control examples.
-
Coalitional Zero-Sum Games for ${H_{\infty}}$ Leader-Following Consensus Control
Leader-following consensus under disturbances is solved by modeling it as a coalitional zero-sum game that yields an H∞ law implementable distributively through GARE decomposition and dynamic average consensus.
-
An Online Learning Approach for Two-Player Zero-Sum Linear Quadratic Games
An online algorithm for zero-sum LQ games with unknown dynamics combines model estimation and surrogate selection to achieve regret bounds on policy convergence.