FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2951990408> ?p ?o ?g. }

• W2951990408 abstract "We study derivative-free methods for policy optimization over the class of linear policies. We focus on characterizing the convergence rate of these methods when applied to linear-quadratic systems, and study various settings of driving noise and reward feedback. We show that these methods provably converge to within any pre-specified tolerance of the optimal policy with a number of zero-order evaluations that is an explicit polynomial of the error tolerance, dimension, and curvature properties of the problem. Our analysis reveals some interesting differences between the settings of additive driving noise and random initialization, as well as the settings of one-point and two-point reward feedback. Our theory is corroborated by extensive simulations of derivative-free methods on these systems. Along the way, we derive convergence rates for stochastic zero-order optimization algorithms when applied to a certain class of non-convex problems." @default.
• W2951990408 created "2019-06-27" @default.
• W2951990408 creator A5003355483 @default.
• W2951990408 creator A5030261391 @default.
• W2951990408 creator A5038379562 @default.
• W2951990408 creator A5046329704 @default.
• W2951990408 creator A5082704866 @default.
• W2951990408 creator A5085869933 @default.
• W2951990408 date "2018-12-20" @default.
• W2951990408 modified "2023-09-27" @default.
• W2951990408 title "Derivative-Free Methods for Policy Optimization: Guarantees for Linear Quadratic Systems" @default.
• W2951990408 cites W1503911522 @default.
• W2951990408 cites W1520597402 @default.
• W2951990408 cites W153281708 @default.
• W2951990408 cites W1595409123 @default.
• W2951990408 cites W1771410628 @default.
• W2951990408 cites W1987217557 @default.
• W2951990408 cites W2004001705 @default.
• W2951990408 cites W2052044664 @default.
• W2951990408 cites W2064076655 @default.
• W2951990408 cites W2068832491 @default.
• W2951990408 cites W2072864444 @default.
• W2951990408 cites W2082210980 @default.
• W2951990408 cites W2098432798 @default.
• W2951990408 cites W2145339207 @default.
• W2951990408 cites W2171830216 @default.
• W2951990408 cites W2173248099 @default.
• W2951990408 cites W2257979135 @default.
• W2951990408 cites W2275844880 @default.
• W2951990408 cites W2596367596 @default.
• W2951990408 cites W2605102758 @default.
• W2951990408 cites W2761923184 @default.
• W2951990408 cites W2768425162 @default.
• W2951990408 cites W2769648743 @default.
• W2951990408 cites W2789525339 @default.
• W2951990408 cites W2794722150 @default.
• W2951990408 cites W2796986421 @default.
• W2951990408 cites W2804569092 @default.
• W2951990408 cites W2886474253 @default.
• W2951990408 cites W2904188377 @default.
• W2951990408 cites W2914234208 @default.
• W2951990408 cites W2949608212 @default.
• W2951990408 cites W2962749646 @default.
• W2951990408 cites W2962861921 @default.
• W2951990408 cites W2963030777 @default.
• W2951990408 cites W2963043564 @default.
• W2951990408 cites W2963062786 @default.
• W2951990408 cites W2963248893 @default.
• W2951990408 cites W2963308146 @default.
• W2951990408 cites W2963470657 @default.
• W2951990408 cites W2963483869 @default.
• W2951990408 cites W2963582321 @default.
• W2951990408 cites W2963681938 @default.
• W2951990408 cites W2964054583 @default.
• W2951990408 cites W2964084913 @default.
• W2951990408 cites W2964161785 @default.
• W2951990408 cites W3035578948 @default.
• W2951990408 cites W53582479 @default.
• W2951990408 hasPublicationYear "2018" @default.
• W2951990408 type Work @default.
• W2951990408 sameAs 2951990408 @default.
• W2951990408 citedByCount "25" @default.
• W2951990408 countsByYear W29519904082019 @default.
• W2951990408 countsByYear W29519904082020 @default.
• W2951990408 countsByYear W29519904082021 @default.
• W2951990408 crossrefType "posted-content" @default.
• W2951990408 hasAuthorship W2951990408A5003355483 @default.
• W2951990408 hasAuthorship W2951990408A5030261391 @default.
• W2951990408 hasAuthorship W2951990408A5038379562 @default.
• W2951990408 hasAuthorship W2951990408A5046329704 @default.
• W2951990408 hasAuthorship W2951990408A5082704866 @default.
• W2951990408 hasAuthorship W2951990408A5085869933 @default.
• W2951990408 hasConcept C112680207 @default.
• W2951990408 hasConcept C114466953 @default.
• W2951990408 hasConcept C126255220 @default.
• W2951990408 hasConcept C127162648 @default.
• W2951990408 hasConcept C134306372 @default.
• W2951990408 hasConcept C137836250 @default.
• W2951990408 hasConcept C157972887 @default.
• W2951990408 hasConcept C162324750 @default.
• W2951990408 hasConcept C194387892 @default.
• W2951990408 hasConcept C199360897 @default.
• W2951990408 hasConcept C202444582 @default.
• W2951990408 hasConcept C2524010 @default.
• W2951990408 hasConcept C2777303404 @default.
• W2951990408 hasConcept C31258907 @default.
• W2951990408 hasConcept C33676613 @default.
• W2951990408 hasConcept C33923547 @default.
• W2951990408 hasConcept C41008148 @default.
• W2951990408 hasConcept C50522688 @default.
• W2951990408 hasConcept C57869625 @default.
• W2951990408 hasConcept C6802819 @default.
• W2951990408 hasConcept C90119067 @default.
• W2951990408 hasConceptScore W2951990408C112680207 @default.
• W2951990408 hasConceptScore W2951990408C114466953 @default.
• W2951990408 hasConceptScore W2951990408C126255220 @default.
• W2951990408 hasConceptScore W2951990408C127162648 @default.
• W2951990408 hasConceptScore W2951990408C134306372 @default.
• W2951990408 hasConceptScore W2951990408C137836250 @default.
• W2951990408 hasConceptScore W2951990408C157972887 @default.

• next