Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100293451> ?p ?o ?g. }
- W3100293451 endingPage "35" @default.
- W3100293451 startingPage "1" @default.
- W3100293451 abstract "With the rapid advance of information technology, network systems have become increasingly complex and hence the underlying system dynamics are often unknown or difficult to characterize. Finding a good network control policy is of significant importance to achieve desirable network performance (e.g., high throughput or low delay). In this work, we consider using model-based reinforcement learning (RL) to learn the optimal control policy for queueing networks so that the average job delay (or equivalently the average queue backlog) is minimized. Traditional approaches in RL, however, cannot handle the unbounded state spaces of the network control problem. To overcome this difficulty, we propose a new algorithm, called RL for Queueing Networks (RL-QN), which applies model-based RL methods over a finite subset of the state space while applying a known stabilizing policy for the rest of the states. We establish that the average queue backlog under RL-QN with an appropriately constructed subset can be arbitrarily close to the optimal result. We evaluate RL-QN in dynamic server allocation, routing, and switching problems. Simulation results show that RL-QN minimizes the average queue backlog effectively." @default.
- W3100293451 created "2020-11-23" @default.
- W3100293451 creator A5008882694 @default.
- W3100293451 creator A5036587377 @default.
- W3100293451 creator A5042253177 @default.
- W3100293451 date "2022-03-31" @default.
- W3100293451 modified "2023-09-26" @default.
- W3100293451 title "RL-QN: A Reinforcement Learning Framework for Optimal Control of Queueing Systems" @default.
- W3100293451 cites W1646707810 @default.
- W3100293451 cites W2003346154 @default.
- W3100293451 cites W2004964364 @default.
- W3100293451 cites W2042216697 @default.
- W3100293451 cites W2042545172 @default.
- W3100293451 cites W2074823898 @default.
- W3100293451 cites W2093892790 @default.
- W3100293451 cites W2095454008 @default.
- W3100293451 cites W2103048107 @default.
- W3100293451 cites W2103098926 @default.
- W3100293451 cites W2120344179 @default.
- W3100293451 cites W2125591683 @default.
- W3100293451 cites W2126878542 @default.
- W3100293451 cites W2132940773 @default.
- W3100293451 cites W2133499361 @default.
- W3100293451 cites W2135663206 @default.
- W3100293451 cites W2157179371 @default.
- W3100293451 cites W2165768656 @default.
- W3100293451 cites W2168739325 @default.
- W3100293451 cites W2293168792 @default.
- W3100293451 cites W2333199285 @default.
- W3100293451 cites W2565612488 @default.
- W3100293451 cites W2612336410 @default.
- W3100293451 cites W2790924949 @default.
- W3100293451 cites W2793477598 @default.
- W3100293451 cites W2898231005 @default.
- W3100293451 cites W2963079995 @default.
- W3100293451 cites W2963561337 @default.
- W3100293451 cites W2963654220 @default.
- W3100293451 cites W2999204576 @default.
- W3100293451 cites W3046060145 @default.
- W3100293451 cites W3099885902 @default.
- W3100293451 cites W3101637649 @default.
- W3100293451 cites W3103882218 @default.
- W3100293451 cites W3105861207 @default.
- W3100293451 cites W3196847620 @default.
- W3100293451 cites W32403112 @default.
- W3100293451 cites W4256307687 @default.
- W3100293451 cites W55761002 @default.
- W3100293451 cites W9378068 @default.
- W3100293451 doi "https://doi.org/10.1145/3529375" @default.
- W3100293451 hasPublicationYear "2022" @default.
- W3100293451 type Work @default.
- W3100293451 sameAs 3100293451 @default.
- W3100293451 citedByCount "0" @default.
- W3100293451 crossrefType "journal-article" @default.
- W3100293451 hasAuthorship W3100293451A5008882694 @default.
- W3100293451 hasAuthorship W3100293451A5036587377 @default.
- W3100293451 hasAuthorship W3100293451A5042253177 @default.
- W3100293451 hasBestOaLocation W31002934511 @default.
- W3100293451 hasConcept C105795698 @default.
- W3100293451 hasConcept C11413529 @default.
- W3100293451 hasConcept C120314980 @default.
- W3100293451 hasConcept C126255220 @default.
- W3100293451 hasConcept C154945302 @default.
- W3100293451 hasConcept C160403385 @default.
- W3100293451 hasConcept C22684755 @default.
- W3100293451 hasConcept C2775924081 @default.
- W3100293451 hasConcept C31258907 @default.
- W3100293451 hasConcept C33891772 @default.
- W3100293451 hasConcept C33923547 @default.
- W3100293451 hasConcept C41008148 @default.
- W3100293451 hasConcept C48103436 @default.
- W3100293451 hasConcept C72434380 @default.
- W3100293451 hasConcept C74172769 @default.
- W3100293451 hasConcept C97541855 @default.
- W3100293451 hasConceptScore W3100293451C105795698 @default.
- W3100293451 hasConceptScore W3100293451C11413529 @default.
- W3100293451 hasConceptScore W3100293451C120314980 @default.
- W3100293451 hasConceptScore W3100293451C126255220 @default.
- W3100293451 hasConceptScore W3100293451C154945302 @default.
- W3100293451 hasConceptScore W3100293451C160403385 @default.
- W3100293451 hasConceptScore W3100293451C22684755 @default.
- W3100293451 hasConceptScore W3100293451C2775924081 @default.
- W3100293451 hasConceptScore W3100293451C31258907 @default.
- W3100293451 hasConceptScore W3100293451C33891772 @default.
- W3100293451 hasConceptScore W3100293451C33923547 @default.
- W3100293451 hasConceptScore W3100293451C41008148 @default.
- W3100293451 hasConceptScore W3100293451C48103436 @default.
- W3100293451 hasConceptScore W3100293451C72434380 @default.
- W3100293451 hasConceptScore W3100293451C74172769 @default.
- W3100293451 hasConceptScore W3100293451C97541855 @default.
- W3100293451 hasFunder F4320337345 @default.
- W3100293451 hasIssue "1" @default.
- W3100293451 hasLocation W31002934511 @default.
- W3100293451 hasLocation W31002934512 @default.
- W3100293451 hasLocation W31002934513 @default.
- W3100293451 hasLocation W31002934514 @default.
- W3100293451 hasOpenAccess W3100293451 @default.
- W3100293451 hasPrimaryLocation W31002934511 @default.