Robust properties of risk-sensitive control
From MaRDI portal
The purpose of this paper is to characterize and prove robustness properties of risk-sensitive controllers precisely. The authors mainly presented the following two results: (1) explicit bounds of the average output power in terms of the input power, (2) a stochastic version of the small gain theorem, which is expressed in terms of the risk-sensitive criterion. In particular, (2) provides a motivation for the use of a risk-sensitive criterion in stochastic robustness.
Recommendations
- Robust output feedback stabilization via risk-sensitive control
- scientific article; zbMATH DE number 1140227
- Some results and problems in risk sensitive stochastic control
- Finite Time--Horizon Risk-Sensitive Control and the Robust Limit under a Quadratic Growth Assumption
- Risk-Sensitive Control of Finite State Machines on an Infinite Horizon I
Cited in
(31)- Some results on risk-sensitive control with full observation
- A robustness result for stochastic control
- Robust output feedback stabilization via risk-sensitive control
- Multi-point Gaussian states, quadratic-exponential cost functionals, and large deviations estimates for linear quantum stochastic systems
- Robust designs through risk sensitivity: an overview
- Robustness to incorrect models and data-driven learning in average-cost optimal stochastic control
- On distributionally robust extreme value analysis
- Robust bounds and optimization at the large deviations scale for queueing models via Rényi divergence
- Exit time risk-sensitive control for systems of cooperative agents
- \(H_{\infty}\)-like control for nonlinear stochastic systems
- State distributions and minimum relative entropy noise sequences in uncertain stochastic systems: the discrete-time case
- H∞control for non-linear stochastic systems: the output-feedback case
- Risk-sensitive control with HARA utility
- Formulation and properties of a divergence used to compare probability measures without absolute continuity
- Quadratic-exponential functionals of Gaussian quantum processes
- Robustness to incorrect system models in stochastic control
- Robustness to approximations and model learning in MDPs and POMDPs
- Quantifying distributional model risk via optimal transport
- Robustness to Incorrect Priors in Partially Observed Stochastic Control
- Infinite-horizon risk-sensitive performance criteria for translation invariant networks of linear quantum stochastic systems
- State-space computation of quadratic-exponential functional rates for linear quantum stochastic systems
- Robust risk‐sensitive control
- Robust decentralized control of coupled systems via risk sensitive control of decoupled or simple models with measure change
- Accelerated gradient methods with biased gradient estimates: risk sensitivity, high-probability guarantees, and large deviation bounds
- Distributionally robust tail bounds based on Wasserstein distance and f-divergence
- Quadratic-exponential coherent feedback control of linear quantum stochastic systems
- Continuous-time risk-sensitive reinforcement learning via quadratic variation penalty
- Robustness of optimal controlled diffusions with near-Brownian noise via rough paths theory
- Entropy bounds for invariant measure perturbations in stochastic systems with uncertain noise
- Control of the multiclass \(\mathrm{G}/\mathrm{G}/1\) queue in the moderate deviation regime
- A differential game formulation of a controlled network
This page was built for publication: Robust properties of risk-sensitive control
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1841265)
