Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems

zbMath1498.93784arXiv1812.08305MaRDI QIDQ4969058

Koulik Khamaru, Kush Bhatia, Martin J. Wainwright, Ashwin Pananjady, Dhruv Malik, Bartlett, Peter L.

Publication date: 5 October 2020

Full work available at URL: https://arxiv.org/abs/1812.08305

zbMATH Keywords

non-convex optimizationderivative-free optimizationlinear quadratic control

Mathematics Subject Classification ID

Nonconvex programming, global optimization (90C26) Learning and adaptive systems in artificial intelligence (68T05) Optimal stochastic control (93E20) Linear-quadratic optimal control problems (49N10)

Related Items

Model-free design of stochastic LQR controller from a primal-dual optimization perspective, Tracking and Regret Bounds for Online Zeroth-Order Euclidean and Riemannian Optimization, Analysis of the optimization landscape of Linear Quadratic Gaussian (LQG) control, Recent Theoretical Advances in Non-Convex Optimization, Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon, Unnamed Item, Policy Optimization for $\mathcal{H}_2$ Linear Control with $\mathcal{H}_\infty$ Robustness Guarantee: Implicit Regularization and Global Convergence, Model-free linear quadratic regulator, Controlled interacting particle algorithms for simulation-based reinforcement learning

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A tail inequality for quadratic forms of subgaussian random vectors
• Linear Thompson sampling revisited
• On the sample complexity of the linear quadratic regulator
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
• Introduction to Stochastic Search and Optimization
• Optimality of Fast-Matching Algorithms for Random Networks With Applications to Structural Controllability
• Optimization of Smooth Functions With Noisy Observations: Local Minimax Rates
• An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
• Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
• Gradient methods for solving equations and inequalities
• A Bound on Tail Probabilities for Quadratic Forms in Independent Random Variables
• Probability