Ergodic-risk criterion for stochastically stabilizing policy optimization

DOI10.1137/25M1733276MaRDI QIDQ7292228zbMATH OpenFDO

Authors Na Li

Publication date 8 July 2026

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/25M1733276

Mathematics Subject Classification ID

Linear-quadratic optimal control problems (49N10) Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Cites work

• Central limit theorem for Markov processes with spectral gap in the Wasserstein metric
• Controlled diffusions with constraints
• Global Convergence of Policy Gradient Primal–Dual Methods for Risk-Constrained LQRs
• scientific article; zbMATH DE number 3723610 (Why is no real title available?)
• Markov Chains and Stochastic Stability
• On Regularizability and Its Application to Online Control of Unstable LTI Systems
• Policy optimization for \(\mathcal{H}_2\) linear control with \(\mathcal{H}_\infty\) robustness guarantee: implicit regularization and global convergence
• Policy optimization over submanifolds for linearly constrained feedback synthesis
• Probability
• Risk-averse model predictive control
• Risk-Aware Linear Quadratic Control Using Conditional Value-at-Risk
• Risk-Constrained Markov Decision Processes
• Risk-constrained reinforcement learning with percentile risk criteria
• Risk-sensitive linear/quadratic/gaussian control
• Stochastic Systems
• Subgradient methods for saddle-point problems
• The policy iteration algorithm for average reward Markov decision processes with general state space

This page was built for publication: Ergodic-risk criterion for stochastically stabilizing policy optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7292228)