Matches in SemOpenAlex for { <https://semopenalex.org/work/W3010042009> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W3010042009 abstract "Network slicing is a key technology in 5G communications system, which aims to dynamically and efficiently allocate resources for diversified services with distinct requirements over a common underlying physical infrastructure. Therein, demand-aware allocation is of significant importance to network slicing. In this paper, we consider a scenario that contains several slices in one base station on sharing the same bandwidth. Deep reinforcement learning (DRL) is leveraged to solve this problem by regarding the varying demands and the allocated bandwidth as the environment emph{state} and emph{action}, respectively. In order to obtain better quality of experience (QoE) satisfaction ratio and spectrum efficiency (SE), we propose generative adversarial network (GAN) based deep distributional Q network (GAN- DDQN) to learn the distribution of state-action values. Furthermore, we estimate the distributions by approximating a full quantile function, which can make the training error more controllable. In order to protect the stability of GAN-DDQN's training process from the widely-spanning utility values, we also put forward a reward-clipping mechanism. Finally, we verify the performance of the proposed GAN-DDQN algorithm through extensive simulations." @default.
- W3010042009 created "2020-03-13" @default.
- W3010042009 creator A5013688157 @default.
- W3010042009 creator A5014842979 @default.
- W3010042009 creator A5036831868 @default.
- W3010042009 creator A5065252700 @default.
- W3010042009 creator A5090543058 @default.
- W3010042009 date "2019-12-01" @default.
- W3010042009 modified "2023-09-24" @default.
- W3010042009 title "GAN-Based Deep Distributional Reinforcement Learning for Resource Management in Network Slicing" @default.
- W3010042009 cites W2145339207 @default.
- W3010042009 cites W2597068831 @default.
- W3010042009 cites W2602923095 @default.
- W3010042009 cites W2612074600 @default.
- W3010042009 cites W2741401130 @default.
- W3010042009 cites W2744111766 @default.
- W3010042009 cites W2744184417 @default.
- W3010042009 cites W2772526503 @default.
- W3010042009 cites W2783558323 @default.
- W3010042009 cites W2900804979 @default.
- W3010042009 cites W32403112 @default.
- W3010042009 cites W4241996101 @default.
- W3010042009 doi "https://doi.org/10.1109/globecom38437.2019.9014217" @default.
- W3010042009 hasPublicationYear "2019" @default.
- W3010042009 type Work @default.
- W3010042009 sameAs 3010042009 @default.
- W3010042009 citedByCount "14" @default.
- W3010042009 countsByYear W30100420092019 @default.
- W3010042009 countsByYear W30100420092020 @default.
- W3010042009 countsByYear W30100420092021 @default.
- W3010042009 countsByYear W30100420092022 @default.
- W3010042009 countsByYear W30100420092023 @default.
- W3010042009 crossrefType "proceedings-article" @default.
- W3010042009 hasAuthorship W3010042009A5013688157 @default.
- W3010042009 hasAuthorship W3010042009A5014842979 @default.
- W3010042009 hasAuthorship W3010042009A5036831868 @default.
- W3010042009 hasAuthorship W3010042009A5065252700 @default.
- W3010042009 hasAuthorship W3010042009A5090543058 @default.
- W3010042009 hasConcept C120314980 @default.
- W3010042009 hasConcept C136764020 @default.
- W3010042009 hasConcept C154945302 @default.
- W3010042009 hasConcept C206345919 @default.
- W3010042009 hasConcept C2776190703 @default.
- W3010042009 hasConcept C2780609101 @default.
- W3010042009 hasConcept C31258907 @default.
- W3010042009 hasConcept C41008148 @default.
- W3010042009 hasConcept C97541855 @default.
- W3010042009 hasConceptScore W3010042009C120314980 @default.
- W3010042009 hasConceptScore W3010042009C136764020 @default.
- W3010042009 hasConceptScore W3010042009C154945302 @default.
- W3010042009 hasConceptScore W3010042009C206345919 @default.
- W3010042009 hasConceptScore W3010042009C2776190703 @default.
- W3010042009 hasConceptScore W3010042009C2780609101 @default.
- W3010042009 hasConceptScore W3010042009C31258907 @default.
- W3010042009 hasConceptScore W3010042009C41008148 @default.
- W3010042009 hasConceptScore W3010042009C97541855 @default.
- W3010042009 hasLocation W30100420091 @default.
- W3010042009 hasOpenAccess W3010042009 @default.
- W3010042009 hasPrimaryLocation W30100420091 @default.
- W3010042009 hasRelatedWork W1485627940 @default.
- W3010042009 hasRelatedWork W1568263432 @default.
- W3010042009 hasRelatedWork W2113059852 @default.
- W3010042009 hasRelatedWork W2152433827 @default.
- W3010042009 hasRelatedWork W3009997038 @default.
- W3010042009 hasRelatedWork W3203982010 @default.
- W3010042009 hasRelatedWork W4283211114 @default.
- W3010042009 hasRelatedWork W4287180973 @default.
- W3010042009 hasRelatedWork W4295941380 @default.
- W3010042009 hasRelatedWork W4304142422 @default.
- W3010042009 isParatext "false" @default.
- W3010042009 isRetracted "false" @default.
- W3010042009 magId "3010042009" @default.
- W3010042009 workType "article" @default.