Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems (Q4969058): Difference between revisions

@@ label / en / label / en @@
+Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems
@@ Property / arXiv classification @@
+cs.LG
@@ Property / arXiv classification: cs.LG / rank @@
+Normal rank
@@ Property / arXiv classification @@
+math.OC
@@ Property / arXiv classification: math.OC / rank @@
+Normal rank
@@ Property / arXiv classification @@
+stat.ML
@@ Property / arXiv classification: stat.ML / rank @@
+Normal rank
@@ Property / arXiv ID @@
+.08305
@@ Property / arXiv ID: 1812.08305 / rank @@
+Normal rank
@@ Property / cites work @@
+Linear Thompson sampling revisited
@@ Property / cites work: Linear Thompson sampling revisited / rank @@
+Normal rank
@@ Property / cites work @@
+Q3376698
@@ Property / cites work: Q3376698 / rank @@
+Normal rank
@@ Property / cites work @@
+On the sample complexity of the linear quadratic regulator
+Normal rank
@@ Property / cites work @@
+Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations
+Normal rank
@@ Property / cites work @@
+Probability
@@ Property / cites work: Probability / rank @@
+Normal rank
@@ Property / cites work @@
+Optimality of Fast-Matching Algorithms for Random Networks With Applications to Structural Controllability
+Normal rank
@@ Property / cites work @@
+Q2921693
@@ Property / cites work: Q2921693 / rank @@
+Normal rank
@@ Property / cites work @@
+Stochastic First- and Zeroth-Order Methods for Nonconvex Stochastic Programming
+Normal rank
@@ Property / cites work @@
+A Bound on Tail Probabilities for Quadratic Forms in Independent Random Variables
+Normal rank
@@ Property / cites work @@
+A tail inequality for quadratic forms of subgaussian random vectors
+Normal rank
@@ Property / cites work @@
+Q3849137
@@ Property / cites work: Q3849137 / rank @@
+Normal rank
@@ Property / cites work @@
+Q2810828
@@ Property / cites work: Q2810828 / rank @@
+Normal rank
@@ Property / cites work @@
+Q5643297
@@ Property / cites work: Q5643297 / rank @@
+Normal rank
@@ Property / cites work @@
+Gradient methods for solving equations and inequalities
+Normal rank
@@ Property / cites work @@
+An Optimal Algorithm for Bandit and Zero-Order Convex Optimization with Two-Point Feedback
+Normal rank
@@ Property / cites work @@
+Introduction to Stochastic Search and Optimization
+Normal rank
@@ Property / cites work @@
+Optimization of Smooth Functions With Noisy Observations: Local Minimax Rates
+Normal rank
@@ Property / cites work @@
+Q4339077
@@ Property / cites work: Q4339077 / rank @@
+Normal rank