Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042368690> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W3042368690 abstract "Multi-objective task scheduling (MOTS) is the task scheduling while optimizing multiple and possibly contradicting constraints. A challenging extension of this problem occurs when every individual task is a multi-objective optimization problem by itself. While deep reinforcement learning (DRL) has been successfully applied to complex sequential problems, its application to the MOTS domain has been stymied by two challenges. The first challenge is the inability of the DRL algorithm to ensure that every item is processed identically regardless of its position in the queue. The second challenge is the need to manage large queues, which results in large neural architectures and long training times. In this study we present MERLIN, a robust, modular and near-optimal DRL-based approach for multi-objective task scheduling. MERLIN applies a hierarchical approach to the MOTS problem by creating one neural network for the processing of individual tasks and another for the scheduling of the overall queue. In addition to being smaller and with shorted training times, the resulting architecture ensures that an item is processed in the same manner regardless of its position in the queue. Additionally, we present a novel approach for efficiently applying DRL-based solutions on very large queues, and demonstrate how we effectively scale MERLIN to process queue sizes that are larger by orders of magnitude than those on which it was trained. Extensive evaluation on multiple queue sizes show that MERLIN outperforms multiple well-known baselines by a large margin (>22%)." @default.
- W3042368690 created "2020-07-23" @default.
- W3042368690 creator A5002391103 @default.
- W3042368690 creator A5043940310 @default.
- W3042368690 creator A5044390999 @default.
- W3042368690 creator A5085792458 @default.
- W3042368690 date "2020-07-17" @default.
- W3042368690 modified "2023-09-27" @default.
- W3042368690 title "Hierarchical Deep Reinforcement Learning Approach for Multi-Objective Scheduling With Varying Queue Sizes" @default.
- W3042368690 cites W1485803169 @default.
- W3042368690 cites W1569029889 @default.
- W3042368690 cites W1585546214 @default.
- W3042368690 cites W1771410628 @default.
- W3042368690 cites W1983220355 @default.
- W3042368690 cites W1988328380 @default.
- W3042368690 cites W1989934867 @default.
- W3042368690 cites W2005604709 @default.
- W3042368690 cites W2026536622 @default.
- W3042368690 cites W2081455098 @default.
- W3042368690 cites W2100787464 @default.
- W3042368690 cites W2121517924 @default.
- W3042368690 cites W2121863487 @default.
- W3042368690 cites W2141559645 @default.
- W3042368690 cites W2145339207 @default.
- W3042368690 cites W2148204686 @default.
- W3042368690 cites W2160371091 @default.
- W3042368690 cites W2506654222 @default.
- W3042368690 cites W2546571074 @default.
- W3042368690 cites W2766447205 @default.
- W3042368690 cites W2778749116 @default.
- W3042368690 cites W2946377411 @default.
- W3042368690 cites W2949608212 @default.
- W3042368690 cites W2964227312 @default.
- W3042368690 cites W2968986602 @default.
- W3042368690 cites W2989021453 @default.
- W3042368690 cites W3026075272 @default.
- W3042368690 cites W3143719465 @default.
- W3042368690 cites W2154697291 @default.
- W3042368690 hasPublicationYear "2020" @default.
- W3042368690 type Work @default.
- W3042368690 sameAs 3042368690 @default.
- W3042368690 citedByCount "0" @default.
- W3042368690 crossrefType "posted-content" @default.
- W3042368690 hasAuthorship W3042368690A5002391103 @default.
- W3042368690 hasAuthorship W3042368690A5043940310 @default.
- W3042368690 hasAuthorship W3042368690A5044390999 @default.
- W3042368690 hasAuthorship W3042368690A5085792458 @default.
- W3042368690 hasConcept C120314980 @default.
- W3042368690 hasConcept C124444977 @default.
- W3042368690 hasConcept C126255220 @default.
- W3042368690 hasConcept C128220111 @default.
- W3042368690 hasConcept C154945302 @default.
- W3042368690 hasConcept C160403385 @default.
- W3042368690 hasConcept C206729178 @default.
- W3042368690 hasConcept C22684755 @default.
- W3042368690 hasConcept C31258907 @default.
- W3042368690 hasConcept C33923547 @default.
- W3042368690 hasConcept C41008148 @default.
- W3042368690 hasConcept C50644808 @default.
- W3042368690 hasConcept C97541855 @default.
- W3042368690 hasConceptScore W3042368690C120314980 @default.
- W3042368690 hasConceptScore W3042368690C124444977 @default.
- W3042368690 hasConceptScore W3042368690C126255220 @default.
- W3042368690 hasConceptScore W3042368690C128220111 @default.
- W3042368690 hasConceptScore W3042368690C154945302 @default.
- W3042368690 hasConceptScore W3042368690C160403385 @default.
- W3042368690 hasConceptScore W3042368690C206729178 @default.
- W3042368690 hasConceptScore W3042368690C22684755 @default.
- W3042368690 hasConceptScore W3042368690C31258907 @default.
- W3042368690 hasConceptScore W3042368690C33923547 @default.
- W3042368690 hasConceptScore W3042368690C41008148 @default.
- W3042368690 hasConceptScore W3042368690C50644808 @default.
- W3042368690 hasConceptScore W3042368690C97541855 @default.
- W3042368690 hasLocation W30423686901 @default.
- W3042368690 hasOpenAccess W3042368690 @default.
- W3042368690 hasPrimaryLocation W30423686901 @default.
- W3042368690 hasRelatedWork W1506047526 @default.
- W3042368690 hasRelatedWork W1548636807 @default.
- W3042368690 hasRelatedWork W1612012483 @default.
- W3042368690 hasRelatedWork W1968117609 @default.
- W3042368690 hasRelatedWork W2008890181 @default.
- W3042368690 hasRelatedWork W2127916556 @default.
- W3042368690 hasRelatedWork W2155225141 @default.
- W3042368690 hasRelatedWork W2182369553 @default.
- W3042368690 hasRelatedWork W2198197423 @default.
- W3042368690 hasRelatedWork W2353643698 @default.
- W3042368690 hasRelatedWork W2393027083 @default.
- W3042368690 hasRelatedWork W2530196122 @default.
- W3042368690 hasRelatedWork W2737164138 @default.
- W3042368690 hasRelatedWork W2810322262 @default.
- W3042368690 hasRelatedWork W3091362456 @default.
- W3042368690 hasRelatedWork W3121761392 @default.
- W3042368690 hasRelatedWork W3197895618 @default.
- W3042368690 hasRelatedWork W3199095686 @default.
- W3042368690 hasRelatedWork W3199463182 @default.
- W3042368690 hasRelatedWork W2607365481 @default.
- W3042368690 isParatext "false" @default.
- W3042368690 isRetracted "false" @default.
- W3042368690 magId "3042368690" @default.
- W3042368690 workType "article" @default.