Reinforcement Learning for Linear-Convex Models with Jumps via Stability Analysis of Feedback Controls

DOI10.1137/21m1414413zbMath1514.93051arXiv2104.09311OpenAlexW4367298538MaRDI QIDQ6042790

Xin Guo, Yu-Fei Zhang, Unnamed Author

Publication date: 4 May 2023

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

Full work available at URL: https://arxiv.org/abs/2104.09311

zbMATH Keywords

Lipschitz stabilityleast-squares estimationjump-diffusioncontinuous-time reinforcement learninglinear-convexsub-Weibull random variable

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stabilization of systems by feedback (93D15)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A convex penalty for switching control of partial differential equations
• Stochastic \(L^1\)-optimal control via forward and backward sampling
• Transportation cost-information inequalities and applications to random dynamical systems and diffusions.
• Continuity of utility maximization under weak convergence
• Concentration inequalities for polynomials in \(\alpha\)-sub-exponential random variables
• On the sample complexity of the linear quadratic regulator
• \(L^p\) estimates for fully coupled FBSDEs with jumps
• Transportation inequalities for stochastic differential equations with jumps
• Sensitivity results in stochastic optimal control: A Lagrangian perspective
• On the Existence of Optimal Controls
• Regularity and Stability of Feedback Relaxed Controls
• Elliptic and Parabolic Second-Order PDEs with Growing Coefficients
• Necessary Conditions for Optimal Control of Stochastic Systems with Random Jumps
• Variational Analysis
• Adaptive continuous-time linear quadratic Gaussian control
• Sparse Solutions in Optimal Control of PDEs with Uncertain Parameters: The Linear Case
• High-Dimensional Probability
• Compactification methods in the control of degenerate diffusions: existence of an optimal control
• Robustness to Incorrect System Models in Stochastic Control
• Exponential Convergence and Stability of Howard's Policy Improvement Algorithm for Controlled Diffusions
• Stochastic Production Planning with Production Constraints
• Moving beyond sub-Gaussianity in high-dimensional statistics: applications in covariance estimation and linear regression