Matches in SemOpenAlex for { <https://semopenalex.org/work/W2953024523> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2953024523 abstract "Network slicing promises to provision diversified services with distinct requirements in one infrastructure. Deep reinforcement learning (e.g., deep $mathcal{Q}$-learning, DQL) is assumed to be an appropriate algorithm to solve the demand-aware inter-slice resource management issue in network slicing by regarding the varying demands and the allocated bandwidth as the environment state and the action, respectively. However, allocating bandwidth in a finer resolution usually implies larger action space, and unfortunately DQL fails to quickly converge in this case. In this paper, we introduce discrete normalized advantage functions (DNAF) into DQL, by separating the $mathcal{Q}$-value function as a state-value function term and an advantage term and exploiting a deterministic policy gradient descent (DPGD) algorithm to avoid the unnecessary calculation of $mathcal{Q}$-value for every state-action pair. Furthermore, as DPGD only works in continuous action space, we embed a k-nearest neighbor algorithm into DQL to quickly find a valid action in the discrete space nearest to the DPGD output. Finally, we verify the faster convergence of the DNAF-based DQL through extensive simulations." @default.
- W2953024523 created "2019-06-27" @default.
- W2953024523 creator A5014708668 @default.
- W2953024523 creator A5014842979 @default.
- W2953024523 creator A5036831868 @default.
- W2953024523 creator A5084947984 @default.
- W2953024523 creator A5090543058 @default.
- W2953024523 date "2019-06-10" @default.
- W2953024523 modified "2023-09-25" @default.
- W2953024523 title "Deep Reinforcement Learning with Discrete Normalized Advantage Functions for Resource Management in Network Slicing" @default.
- W2953024523 cites W2048570986 @default.
- W2953024523 cites W2121863487 @default.
- W2953024523 cites W2145339207 @default.
- W2953024523 cites W2155968351 @default.
- W2953024523 cites W2165150801 @default.
- W2953024523 cites W2173248099 @default.
- W2953024523 cites W2201581102 @default.
- W2953024523 cites W2215378786 @default.
- W2953024523 cites W2602923095 @default.
- W2953024523 cites W2744111766 @default.
- W2953024523 cites W2900804979 @default.
- W2953024523 cites W2914177182 @default.
- W2953024523 cites W2950471160 @default.
- W2953024523 cites W2951799221 @default.
- W2953024523 cites W3146803896 @default.
- W2953024523 doi "https://doi.org/10.48550/arxiv.1906.04594" @default.
- W2953024523 hasPublicationYear "2019" @default.
- W2953024523 type Work @default.
- W2953024523 sameAs 2953024523 @default.
- W2953024523 citedByCount "2" @default.
- W2953024523 countsByYear W29530245232019 @default.
- W2953024523 countsByYear W29530245232021 @default.
- W2953024523 crossrefType "posted-content" @default.
- W2953024523 hasAuthorship W2953024523A5014708668 @default.
- W2953024523 hasAuthorship W2953024523A5014842979 @default.
- W2953024523 hasAuthorship W2953024523A5036831868 @default.
- W2953024523 hasAuthorship W2953024523A5084947984 @default.
- W2953024523 hasAuthorship W2953024523A5090543058 @default.
- W2953024523 hasBestOaLocation W29530245231 @default.
- W2953024523 hasConcept C105795698 @default.
- W2953024523 hasConcept C111919701 @default.
- W2953024523 hasConcept C126255220 @default.
- W2953024523 hasConcept C136764020 @default.
- W2953024523 hasConcept C14646407 @default.
- W2953024523 hasConcept C154945302 @default.
- W2953024523 hasConcept C188116033 @default.
- W2953024523 hasConcept C2776190703 @default.
- W2953024523 hasConcept C2778572836 @default.
- W2953024523 hasConcept C33923547 @default.
- W2953024523 hasConcept C41008148 @default.
- W2953024523 hasConcept C72434380 @default.
- W2953024523 hasConcept C80444323 @default.
- W2953024523 hasConcept C97541855 @default.
- W2953024523 hasConceptScore W2953024523C105795698 @default.
- W2953024523 hasConceptScore W2953024523C111919701 @default.
- W2953024523 hasConceptScore W2953024523C126255220 @default.
- W2953024523 hasConceptScore W2953024523C136764020 @default.
- W2953024523 hasConceptScore W2953024523C14646407 @default.
- W2953024523 hasConceptScore W2953024523C154945302 @default.
- W2953024523 hasConceptScore W2953024523C188116033 @default.
- W2953024523 hasConceptScore W2953024523C2776190703 @default.
- W2953024523 hasConceptScore W2953024523C2778572836 @default.
- W2953024523 hasConceptScore W2953024523C33923547 @default.
- W2953024523 hasConceptScore W2953024523C41008148 @default.
- W2953024523 hasConceptScore W2953024523C72434380 @default.
- W2953024523 hasConceptScore W2953024523C80444323 @default.
- W2953024523 hasConceptScore W2953024523C97541855 @default.
- W2953024523 hasLocation W29530245231 @default.
- W2953024523 hasOpenAccess W2953024523 @default.
- W2953024523 hasPrimaryLocation W29530245231 @default.
- W2953024523 hasRelatedWork W1583080569 @default.
- W2953024523 hasRelatedWork W1592209052 @default.
- W2953024523 hasRelatedWork W1621708194 @default.
- W2953024523 hasRelatedWork W2120968583 @default.
- W2953024523 hasRelatedWork W2151416233 @default.
- W2953024523 hasRelatedWork W2383312578 @default.
- W2953024523 hasRelatedWork W2569146624 @default.
- W2953024523 hasRelatedWork W2937181779 @default.
- W2953024523 hasRelatedWork W2952685986 @default.
- W2953024523 hasRelatedWork W3033762800 @default.
- W2953024523 isParatext "false" @default.
- W2953024523 isRetracted "false" @default.
- W2953024523 magId "2953024523" @default.
- W2953024523 workType "article" @default.