{"total":17,"rows":[{"id":"2404.10851","title":"Sample Complexity of the Linear Quadratic Regulator: A Reinforcement Learning Lens","created":"2024-04-16","cited_by_count":8,"area":"deeprl"},{"id":"2505.03706","title":"Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches","created":"2025-05-06","cited_by_count":5,"area":"deeprl"},{"id":"2404.09061","title":"Asynchronous Heterogeneous Linear Quadratic Regulator Design","created":"2024-04-13","cited_by_count":4,"area":"deeprl"},{"id":"2602.01460","title":"Non-Uniform Noise-to-Signal Ratio in the REINFORCE Policy-Gradient Estimator","created":"2026-02-01","cited_by_count":4,"area":"deeprl"},{"id":"2407.06418","title":"System stabilization with policy optimization on unstable latent manifolds","created":"2024-07-08","cited_by_count":2,"area":"deeprl"},{"id":"2502.19977","title":"Convergence Guarantees of Model-free Policy Gradient Methods for LQR with Stochastic Data","created":"2025-02-27","cited_by_count":2,"area":"deeprl"},{"id":"2403.05367","title":"Stability-Certified On-Policy Data-Driven LQR via Recursive Learning and Policy Gradient","created":"2024-03-08","cited_by_count":1,"area":"deeprl"},{"id":"2407.03233","title":"Asynchronous Parallel Policy Gradient Methods for the Linear Quadratic Regulator","created":"2024-07-03","cited_by_count":1,"area":"deeprl"},{"id":"2506.12596","title":"On the Robustness of Derivative-free Methods for Linear Quadratic Regulator","created":"2025-06-14","cited_by_count":1,"area":"deeprl"},{"id":"2510.19141","title":"Policy Gradient Method for LQG Control via Input-Output-History Representation: Convergence to $O(\\epsilon)$-Stationary Points","created":"2025-10-22","cited_by_count":1,"area":"deeprl"},{"id":"2601.19284","title":"Model-Free Output Feedback Stabilization via Policy Gradient Methods","created":"2026-01-27","cited_by_count":1,"area":"deeprl"},{"id":"2604.16730","title":"Multitask LQG Control: Performance and Generalization Bounds","created":"2026-04-17","cited_by_count":1,"area":"deeprl"},{"id":"2404.11382","title":"Convergence of Policy Gradient for Stochastic Linear-Quadratic Control Problem in Infinite Horizon","created":"2024-04-17","cited_by_count":0,"area":"deeprl"},{"id":"2507.10452","title":"Some remarks on gradient dominance and LQR policy optimization","created":"2025-07-14","cited_by_count":0,"area":"deeprl"},{"id":"2601.03016","title":"Adaptive Control of Unknown Linear Switched Systems via Policy Gradient Methods","created":"2026-01-06","cited_by_count":0,"area":"deeprl"},{"id":"2604.10635","title":"On the Optimization Landscape of Observer-based Dynamic Linear Quadratic Control","created":"2026-04-12","cited_by_count":0,"area":"deeprl"},{"id":"2605.26640","title":"Sample Complexity of Policy Gradient for Log-Growth Control","created":"2026-05-26","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}