Matches in SemOpenAlex for { <https://semopenalex.org/work/W3161037238> ?p ?o ?g. }
- W3161037238 endingPage "17524" @default.
- W3161037238 startingPage "17508" @default.
- W3161037238 abstract "This article studies the joint optimization problem of computation offloading and resource allocation (JCORA) in mobile-edge computing (MEC). Deep reinforcement learning (DRL) is one of the ideal techniques for addressing the dynamic JCORA problem. However, it is still challenging to adapt traditional DRL methods for the problem since they usually lead to slow and unstable convergence in model training. To this end, we propose a temporal attentional deterministic policy gradient (TADPG) to tackle JCORA. Based on the deep deterministic policy gradient (DDPG), TADPG has two significant features. First, a temporal feature extraction network consisting of a 1-D convolution (Conv1D) residual block and an attentional long short-term memory (LSTM) network is designed, which is beneficial to high-quality state representation and function approximation. Second, a rank-based prioritized experience replay (rPER) method is devised to accelerate and stabilize the convergence of model training. Experimental results demonstrate that the decentralized TADPG-based mechanism can achieve more efficient JCORA performance than the centralized one, and the proposed TADPG outperforms a number of state-of-the-art DRL agents in terms of the task completion time and energy consumption." @default.
- W3161037238 created "2021-05-24" @default.
- W3161037238 creator A5007865788 @default.
- W3161037238 creator A5026071162 @default.
- W3161037238 creator A5050203956 @default.
- W3161037238 creator A5052342599 @default.
- W3161037238 creator A5061307388 @default.
- W3161037238 date "2021-12-15" @default.
- W3161037238 modified "2023-10-16" @default.
- W3161037238 title "A DRL Agent for Jointly Optimizing Computation Offloading and Resource Allocation in MEC" @default.
- W3161037238 cites W2064675550 @default.
- W3161037238 cites W2076063813 @default.
- W3161037238 cites W2194775991 @default.
- W3161037238 cites W2585425668 @default.
- W3161037238 cites W2624989916 @default.
- W3161037238 cites W2770446450 @default.
- W3161037238 cites W2781935635 @default.
- W3161037238 cites W2794343007 @default.
- W3161037238 cites W2808381205 @default.
- W3161037238 cites W2808449107 @default.
- W3161037238 cites W2891894830 @default.
- W3161037238 cites W2897066997 @default.
- W3161037238 cites W2905026759 @default.
- W3161037238 cites W2942267387 @default.
- W3161037238 cites W2955097190 @default.
- W3161037238 cites W2955103784 @default.
- W3161037238 cites W2955251534 @default.
- W3161037238 cites W2956914641 @default.
- W3161037238 cites W2959276766 @default.
- W3161037238 cites W2963001767 @default.
- W3161037238 cites W2963334314 @default.
- W3161037238 cites W2963549123 @default.
- W3161037238 cites W2964015972 @default.
- W3161037238 cites W2964054168 @default.
- W3161037238 cites W2980626082 @default.
- W3161037238 cites W3010178570 @default.
- W3161037238 cites W3010742418 @default.
- W3161037238 cites W3012434840 @default.
- W3161037238 cites W3012977606 @default.
- W3161037238 cites W3015366655 @default.
- W3161037238 cites W3017186664 @default.
- W3161037238 cites W3026805356 @default.
- W3161037238 cites W3035007032 @default.
- W3161037238 cites W3045546031 @default.
- W3161037238 cites W3045601523 @default.
- W3161037238 cites W3106445841 @default.
- W3161037238 cites W3112262420 @default.
- W3161037238 cites W3124943657 @default.
- W3161037238 cites W4232345992 @default.
- W3161037238 cites W4245108548 @default.
- W3161037238 doi "https://doi.org/10.1109/jiot.2021.3081694" @default.
- W3161037238 hasPublicationYear "2021" @default.
- W3161037238 type Work @default.
- W3161037238 sameAs 3161037238 @default.
- W3161037238 citedByCount "81" @default.
- W3161037238 countsByYear W31610372382021 @default.
- W3161037238 countsByYear W31610372382022 @default.
- W3161037238 countsByYear W31610372382023 @default.
- W3161037238 crossrefType "journal-article" @default.
- W3161037238 hasAuthorship W3161037238A5007865788 @default.
- W3161037238 hasAuthorship W3161037238A5026071162 @default.
- W3161037238 hasAuthorship W3161037238A5050203956 @default.
- W3161037238 hasAuthorship W3161037238A5052342599 @default.
- W3161037238 hasAuthorship W3161037238A5061307388 @default.
- W3161037238 hasConcept C11413529 @default.
- W3161037238 hasConcept C126255220 @default.
- W3161037238 hasConcept C154945302 @default.
- W3161037238 hasConcept C155512373 @default.
- W3161037238 hasConcept C162307627 @default.
- W3161037238 hasConcept C162324750 @default.
- W3161037238 hasConcept C2777303404 @default.
- W3161037238 hasConcept C2778456923 @default.
- W3161037238 hasConcept C2781041963 @default.
- W3161037238 hasConcept C29202148 @default.
- W3161037238 hasConcept C31258907 @default.
- W3161037238 hasConcept C33923547 @default.
- W3161037238 hasConcept C41008148 @default.
- W3161037238 hasConcept C45347329 @default.
- W3161037238 hasConcept C45374587 @default.
- W3161037238 hasConcept C50522688 @default.
- W3161037238 hasConcept C50644808 @default.
- W3161037238 hasConcept C97541855 @default.
- W3161037238 hasConceptScore W3161037238C11413529 @default.
- W3161037238 hasConceptScore W3161037238C126255220 @default.
- W3161037238 hasConceptScore W3161037238C154945302 @default.
- W3161037238 hasConceptScore W3161037238C155512373 @default.
- W3161037238 hasConceptScore W3161037238C162307627 @default.
- W3161037238 hasConceptScore W3161037238C162324750 @default.
- W3161037238 hasConceptScore W3161037238C2777303404 @default.
- W3161037238 hasConceptScore W3161037238C2778456923 @default.
- W3161037238 hasConceptScore W3161037238C2781041963 @default.
- W3161037238 hasConceptScore W3161037238C29202148 @default.
- W3161037238 hasConceptScore W3161037238C31258907 @default.
- W3161037238 hasConceptScore W3161037238C33923547 @default.
- W3161037238 hasConceptScore W3161037238C41008148 @default.
- W3161037238 hasConceptScore W3161037238C45347329 @default.
- W3161037238 hasConceptScore W3161037238C45374587 @default.
- W3161037238 hasConceptScore W3161037238C50522688 @default.