FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4225697670> ?p ?o ?g. }

• W4225697670 endingPage "4825" @default.
• W4225697670 startingPage "4816" @default.
• W4225697670 abstract "Extracting temporal abstraction (option), which empowers the action space, is a crucial challenge in hierarchical reinforcement learning. Under a well-structured action space, decision-making agents can probe more deeply in the searching or plan efficiently through pruning irrelevant action candidates. However, automatically capturing a well-performed temporal abstraction is a nontrivial challenge due to its insufficient exploration and inadequate functionality. We consider alleviating this challenge from two perspectives, i.e., diversity and individuality. For the aspect of diversity, we propose a maximum entropy model based on ensembled options to encourage exploration. For the aspect of individuality, we propose to distinguish each option accurately, utilizing mutual formation minimization, so that each option can better express and function. We name our framework as an ensemble with soft option (ESO) critics. Furthermore, the residual algorithm (RA) with a bidirectional target network is introduced to stabilize bootstrapping, yielding a residual version of ESO. We provide detailed analysis for extensive experiments, which shows that our method boosts performance in commonly used continuous control tasks." @default.
• W4225697670 created "2022-05-05" @default.
• W4225697670 creator A5021744453 @default.
• W4225697670 creator A5042441491 @default.
• W4225697670 creator A5065413088 @default.
• W4225697670 creator A5072350518 @default.
• W4225697670 creator A5081872546 @default.
• W4225697670 date "2023-08-01" @default.
• W4225697670 modified "2023-10-02" @default.
• W4225697670 title "Empowering the Diversity and Individuality of Option: Residual Soft Option Critic Framework" @default.
• W4225697670 cites W1646707810 @default.
• W4225697670 cites W2101881799 @default.
• W4225697670 cites W2109910161 @default.
• W4225697670 cites W2132714442 @default.
• W4225697670 cites W2145339207 @default.
• W4225697670 cites W2158782408 @default.
• W4225697670 cites W2257979135 @default.
• W4225697670 cites W2739678353 @default.
• W4225697670 cites W2791797404 @default.
• W4225697670 cites W2889939141 @default.
• W4225697670 cites W2963430540 @default.
• W4225697670 cites W2963761387 @default.
• W4225697670 cites W2964227312 @default.
• W4225697670 cites W2965889088 @default.
• W4225697670 cites W3110074314 @default.
• W4225697670 doi "https://doi.org/10.1109/tnnls.2021.3128666" @default.
• W4225697670 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34851834" @default.
• W4225697670 hasPublicationYear "2023" @default.
• W4225697670 type Work @default.
• W4225697670 citedByCount "2" @default.
• W4225697670 countsByYear W42256976702022 @default.
• W4225697670 crossrefType "journal-article" @default.
• W4225697670 hasAuthorship W4225697670A5021744453 @default.
• W4225697670 hasAuthorship W4225697670A5042441491 @default.
• W4225697670 hasAuthorship W4225697670A5065413088 @default.
• W4225697670 hasAuthorship W4225697670A5072350518 @default.
• W4225697670 hasAuthorship W4225697670A5081872546 @default.
• W4225697670 hasBestOaLocation W42256976701 @default.
• W4225697670 hasConcept C106301342 @default.
• W4225697670 hasConcept C108010975 @default.
• W4225697670 hasConcept C111472728 @default.
• W4225697670 hasConcept C111919701 @default.
• W4225697670 hasConcept C11413529 @default.
• W4225697670 hasConcept C119857082 @default.
• W4225697670 hasConcept C121332964 @default.
• W4225697670 hasConcept C124304363 @default.
• W4225697670 hasConcept C138885662 @default.
• W4225697670 hasConcept C144024400 @default.
• W4225697670 hasConcept C154945302 @default.
• W4225697670 hasConcept C155512373 @default.
• W4225697670 hasConcept C19165224 @default.
• W4225697670 hasConcept C2778572836 @default.
• W4225697670 hasConcept C2780791683 @default.
• W4225697670 hasConcept C2781316041 @default.
• W4225697670 hasConcept C41008148 @default.
• W4225697670 hasConcept C62520636 @default.
• W4225697670 hasConcept C6557445 @default.
• W4225697670 hasConcept C86803240 @default.
• W4225697670 hasConcept C97541855 @default.
• W4225697670 hasConceptScore W4225697670C106301342 @default.
• W4225697670 hasConceptScore W4225697670C108010975 @default.
• W4225697670 hasConceptScore W4225697670C111472728 @default.
• W4225697670 hasConceptScore W4225697670C111919701 @default.
• W4225697670 hasConceptScore W4225697670C11413529 @default.
• W4225697670 hasConceptScore W4225697670C119857082 @default.
• W4225697670 hasConceptScore W4225697670C121332964 @default.
• W4225697670 hasConceptScore W4225697670C124304363 @default.
• W4225697670 hasConceptScore W4225697670C138885662 @default.
• W4225697670 hasConceptScore W4225697670C144024400 @default.
• W4225697670 hasConceptScore W4225697670C154945302 @default.
• W4225697670 hasConceptScore W4225697670C155512373 @default.
• W4225697670 hasConceptScore W4225697670C19165224 @default.
• W4225697670 hasConceptScore W4225697670C2778572836 @default.
• W4225697670 hasConceptScore W4225697670C2780791683 @default.
• W4225697670 hasConceptScore W4225697670C2781316041 @default.
• W4225697670 hasConceptScore W4225697670C41008148 @default.
• W4225697670 hasConceptScore W4225697670C62520636 @default.
• W4225697670 hasConceptScore W4225697670C6557445 @default.
• W4225697670 hasConceptScore W4225697670C86803240 @default.
• W4225697670 hasConceptScore W4225697670C97541855 @default.
• W4225697670 hasFunder F4320321001 @default.
• W4225697670 hasIssue "8" @default.
• W4225697670 hasLocation W42256976701 @default.
• W4225697670 hasLocation W42256976702 @default.
• W4225697670 hasOpenAccess W4225697670 @default.
• W4225697670 hasPrimaryLocation W42256976701 @default.
• W4225697670 hasRelatedWork W260766989 @default.
• W4225697670 hasRelatedWork W2943121983 @default.
• W4225697670 hasRelatedWork W2959276766 @default.
• W4225697670 hasRelatedWork W2961085424 @default.
• W4225697670 hasRelatedWork W3037298662 @default.
• W4225697670 hasRelatedWork W3074294383 @default.
• W4225697670 hasRelatedWork W3139193008 @default.
• W4225697670 hasRelatedWork W4206669594 @default.
• W4225697670 hasRelatedWork W4295941380 @default.
• W4225697670 hasRelatedWork W4319083788 @default.
• W4225697670 hasVolume "34" @default.
• W4225697670 isParatext "false" @default.

• next