Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386945787> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4386945787 endingPage "100951" @default.
- W4386945787 startingPage "100951" @default.
- W4386945787 abstract "Hierarchical reinforcement learning (HRL) is a promising approach for efficiently solving various long-horizon decision-making tasks in the Internet of Things (IoT) domain. However, HRL algorithms are known to rely on expert knowledge to preset an appropriate hierarchical structure for different IoT tasks, which leads to higher trial costs and limits its wider application. In this paper, we propose a new method called DHRL (Dynamic-Level Hierarchical Reinforcement Learning) and it is able to adaptively search for the optimal hierarchical structure while maintaining the generality of framework design. DHRL incorporates an embedded exploration and exploitation mechanism that effectively solves the challenges caused by dependence between different levels and achieves a balance between maximizing benefits and current evaluation accuracy. Nonetheless, the more exploration processes inevitably has a negative impact on the performance. To mitigate this influences, we propose a synchronous training architecture to support DHRL operating in a distributed and parallel manner, in which the adaptive evolutionary method is also introduced to accelerate the convergence. Extensive experimental evaluations are conducted to demonstrate the effectiveness of our theory and method." @default.
- W4386945787 created "2023-09-23" @default.
- W4386945787 creator A5001977610 @default.
- W4386945787 creator A5002192584 @default.
- W4386945787 creator A5003633201 @default.
- W4386945787 creator A5013357648 @default.
- W4386945787 creator A5042204573 @default.
- W4386945787 creator A5043091074 @default.
- W4386945787 creator A5063946308 @default.
- W4386945787 date "2023-09-01" @default.
- W4386945787 modified "2023-10-16" @default.
- W4386945787 title "Towards efficient long-horizon decision-making using automated structure search method of hierarchical reinforcement learning for edge artificial intelligence" @default.
- W4386945787 cites W2109910161 @default.
- W4386945787 cites W2112420033 @default.
- W4386945787 cites W2121517924 @default.
- W4386945787 cites W2170198047 @default.
- W4386945787 cites W2604213794 @default.
- W4386945787 cites W2766447205 @default.
- W4386945787 cites W2899620415 @default.
- W4386945787 cites W2962937819 @default.
- W4386945787 cites W2964227312 @default.
- W4386945787 cites W2964505566 @default.
- W4386945787 cites W2964700358 @default.
- W4386945787 cites W2998443480 @default.
- W4386945787 doi "https://doi.org/10.1016/j.iot.2023.100951" @default.
- W4386945787 hasPublicationYear "2023" @default.
- W4386945787 type Work @default.
- W4386945787 citedByCount "0" @default.
- W4386945787 crossrefType "journal-article" @default.
- W4386945787 hasAuthorship W4386945787A5001977610 @default.
- W4386945787 hasAuthorship W4386945787A5002192584 @default.
- W4386945787 hasAuthorship W4386945787A5003633201 @default.
- W4386945787 hasAuthorship W4386945787A5013357648 @default.
- W4386945787 hasAuthorship W4386945787A5042204573 @default.
- W4386945787 hasAuthorship W4386945787A5043091074 @default.
- W4386945787 hasAuthorship W4386945787A5063946308 @default.
- W4386945787 hasConcept C119857082 @default.
- W4386945787 hasConcept C126255220 @default.
- W4386945787 hasConcept C134306372 @default.
- W4386945787 hasConcept C154945302 @default.
- W4386945787 hasConcept C15744967 @default.
- W4386945787 hasConcept C162307627 @default.
- W4386945787 hasConcept C162324750 @default.
- W4386945787 hasConcept C2777303404 @default.
- W4386945787 hasConcept C2780767217 @default.
- W4386945787 hasConcept C28761237 @default.
- W4386945787 hasConcept C33923547 @default.
- W4386945787 hasConcept C36503486 @default.
- W4386945787 hasConcept C41008148 @default.
- W4386945787 hasConcept C50522688 @default.
- W4386945787 hasConcept C542102704 @default.
- W4386945787 hasConcept C97541855 @default.
- W4386945787 hasConceptScore W4386945787C119857082 @default.
- W4386945787 hasConceptScore W4386945787C126255220 @default.
- W4386945787 hasConceptScore W4386945787C134306372 @default.
- W4386945787 hasConceptScore W4386945787C154945302 @default.
- W4386945787 hasConceptScore W4386945787C15744967 @default.
- W4386945787 hasConceptScore W4386945787C162307627 @default.
- W4386945787 hasConceptScore W4386945787C162324750 @default.
- W4386945787 hasConceptScore W4386945787C2777303404 @default.
- W4386945787 hasConceptScore W4386945787C2780767217 @default.
- W4386945787 hasConceptScore W4386945787C28761237 @default.
- W4386945787 hasConceptScore W4386945787C33923547 @default.
- W4386945787 hasConceptScore W4386945787C36503486 @default.
- W4386945787 hasConceptScore W4386945787C41008148 @default.
- W4386945787 hasConceptScore W4386945787C50522688 @default.
- W4386945787 hasConceptScore W4386945787C542102704 @default.
- W4386945787 hasConceptScore W4386945787C97541855 @default.
- W4386945787 hasFunder F4320321001 @default.
- W4386945787 hasLocation W43869457871 @default.
- W4386945787 hasOpenAccess W4386945787 @default.
- W4386945787 hasPrimaryLocation W43869457871 @default.
- W4386945787 hasRelatedWork W2156232164 @default.
- W4386945787 hasRelatedWork W2803281228 @default.
- W4386945787 hasRelatedWork W2950614095 @default.
- W4386945787 hasRelatedWork W2959276766 @default.
- W4386945787 hasRelatedWork W2961085424 @default.
- W4386945787 hasRelatedWork W3074294383 @default.
- W4386945787 hasRelatedWork W4206669594 @default.
- W4386945787 hasRelatedWork W4294567340 @default.
- W4386945787 hasRelatedWork W4295941380 @default.
- W4386945787 hasRelatedWork W4319083788 @default.
- W4386945787 isParatext "false" @default.
- W4386945787 isRetracted "false" @default.
- W4386945787 workType "article" @default.