RAID framework uses switching incentives and least-squares estimation to achieve O(t^{-0.5}) parameter rates and O(t^{0.5} log t) regret in nonlinear games with private costs.
Online learning for nonlinear dynamical systems without the i.i.d. condition,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A nonlinear WLS-based adaptive controller achieves almost-sure global stability and long-run average tracking for nonlinearly parameterized stochastic systems without persistent excitation.
citing papers explorer
-
A No-Regret Framework for Adaptive Incentive Design
RAID framework uses switching incentives and least-squares estimation to achieve O(t^{-0.5}) parameter rates and O(t^{0.5} log t) regret in nonlinear games with private costs.
-
Stochastic Adaptive Control for Systems with Nonlinear Parameterization: Almost Sure Stability and Tracking
A nonlinear WLS-based adaptive controller achieves almost-sure global stability and long-run average tracking for nonlinearly parameterized stochastic systems without persistent excitation.