Matches in SemOpenAlex for { <https://semopenalex.org/work/W2896048729> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2896048729 abstract "Reinforcement learning (RL) is used to directly design a control policy using data collected from the system. This paper considers the robustness of controllers trained via model-free RL. The discussion focuses on the standard model-based linear quadratic Gaussian (LQG) problem as a special instance of RL. A simple example, originally formulated for LQG problems, is used to demonstrate that RL with partial observations can lead to poor robustness margins. It is proposed to recover robustness by introducing random perturbations at the system input during the RL training. The perturbation magnitude can be used to trade off performance for robustness. Two simple examples are presented to demonstrate the proposed method for enhancing robustness during RL training." @default.
- W2896048729 created "2018-10-26" @default.
- W2896048729 creator A5009028512 @default.
- W2896048729 creator A5044834331 @default.
- W2896048729 date "2018-10-22" @default.
- W2896048729 modified "2023-09-27" @default.
- W2896048729 title "Recovering Robustness in Model-Free Reinforcement learning" @default.
- W2896048729 cites W1522531528 @default.
- W2896048729 cites W1530751895 @default.
- W2896048729 cites W1868559974 @default.
- W2896048729 cites W1965640670 @default.
- W2896048729 cites W1997177885 @default.
- W2896048729 cites W2030033366 @default.
- W2896048729 cites W2073384958 @default.
- W2896048729 cites W2081166534 @default.
- W2896048729 cites W2098695330 @default.
- W2896048729 cites W2103313140 @default.
- W2896048729 cites W2108734173 @default.
- W2896048729 cites W2112970167 @default.
- W2896048729 cites W2121863487 @default.
- W2896048729 cites W2127107099 @default.
- W2896048729 cites W2147828974 @default.
- W2896048729 cites W2757789407 @default.
- W2896048729 cites W2761923184 @default.
- W2896048729 cites W2810785043 @default.
- W2896048729 cites W2951222758 @default.
- W2896048729 cites W3216747129 @default.
- W2896048729 hasPublicationYear "2018" @default.
- W2896048729 type Work @default.
- W2896048729 sameAs 2896048729 @default.
- W2896048729 citedByCount "1" @default.
- W2896048729 countsByYear W28960487292019 @default.
- W2896048729 crossrefType "posted-content" @default.
- W2896048729 hasAuthorship W2896048729A5009028512 @default.
- W2896048729 hasAuthorship W2896048729A5044834331 @default.
- W2896048729 hasConcept C104317684 @default.
- W2896048729 hasConcept C121332964 @default.
- W2896048729 hasConcept C126255220 @default.
- W2896048729 hasConcept C154945302 @default.
- W2896048729 hasConcept C163716315 @default.
- W2896048729 hasConcept C177918212 @default.
- W2896048729 hasConcept C185592680 @default.
- W2896048729 hasConcept C204495892 @default.
- W2896048729 hasConcept C2775924081 @default.
- W2896048729 hasConcept C33923547 @default.
- W2896048729 hasConcept C41008148 @default.
- W2896048729 hasConcept C47446073 @default.
- W2896048729 hasConcept C55493867 @default.
- W2896048729 hasConcept C62520636 @default.
- W2896048729 hasConcept C63479239 @default.
- W2896048729 hasConcept C97541855 @default.
- W2896048729 hasConcept C98779006 @default.
- W2896048729 hasConceptScore W2896048729C104317684 @default.
- W2896048729 hasConceptScore W2896048729C121332964 @default.
- W2896048729 hasConceptScore W2896048729C126255220 @default.
- W2896048729 hasConceptScore W2896048729C154945302 @default.
- W2896048729 hasConceptScore W2896048729C163716315 @default.
- W2896048729 hasConceptScore W2896048729C177918212 @default.
- W2896048729 hasConceptScore W2896048729C185592680 @default.
- W2896048729 hasConceptScore W2896048729C204495892 @default.
- W2896048729 hasConceptScore W2896048729C2775924081 @default.
- W2896048729 hasConceptScore W2896048729C33923547 @default.
- W2896048729 hasConceptScore W2896048729C41008148 @default.
- W2896048729 hasConceptScore W2896048729C47446073 @default.
- W2896048729 hasConceptScore W2896048729C55493867 @default.
- W2896048729 hasConceptScore W2896048729C62520636 @default.
- W2896048729 hasConceptScore W2896048729C63479239 @default.
- W2896048729 hasConceptScore W2896048729C97541855 @default.
- W2896048729 hasConceptScore W2896048729C98779006 @default.
- W2896048729 hasLocation W28960487291 @default.
- W2896048729 hasOpenAccess W2896048729 @default.
- W2896048729 hasPrimaryLocation W28960487291 @default.
- W2896048729 hasRelatedWork W1593778274 @default.
- W2896048729 hasRelatedWork W2000670364 @default.
- W2896048729 hasRelatedWork W2014977497 @default.
- W2896048729 hasRelatedWork W2099767582 @default.
- W2896048729 hasRelatedWork W2105792961 @default.
- W2896048729 hasRelatedWork W2143346970 @default.
- W2896048729 hasRelatedWork W2592001929 @default.
- W2896048729 hasRelatedWork W2708535305 @default.
- W2896048729 hasRelatedWork W2754412812 @default.
- W2896048729 hasRelatedWork W2909601460 @default.
- W2896048729 hasRelatedWork W3005095811 @default.
- W2896048729 hasRelatedWork W3011994177 @default.
- W2896048729 hasRelatedWork W3120111328 @default.
- W2896048729 hasRelatedWork W3127454018 @default.
- W2896048729 hasRelatedWork W3144645906 @default.
- W2896048729 hasRelatedWork W3150527705 @default.
- W2896048729 hasRelatedWork W3164586158 @default.
- W2896048729 hasRelatedWork W3202294003 @default.
- W2896048729 hasRelatedWork W3208318794 @default.
- W2896048729 hasRelatedWork W3134090123 @default.
- W2896048729 isParatext "false" @default.
- W2896048729 isRetracted "false" @default.
- W2896048729 magId "2896048729" @default.
- W2896048729 workType "article" @default.