FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1574700590> ?p ?o ?g. }

• W1574700590 endingPage "262" @default.
• W1574700590 startingPage "235" @default.
• W1574700590 abstract "Recent algorithmic and theoretical advances in reinforcement learning (RL) have attracted widespread interest. RL algorithms have appeared that approximate dynamic programming on an incremental basis. They can be trained on the basis of real or simulated experiences, focusing their computation on areas of state space that are actually visited during control, making them computationally tractable on very large problems. If each member of a team of agents employs one of these algorithms, a new collective learning algorithm emerges for the team as a whole. In this paper we demonstrate that such collective RL algorithms can be powerful heuristic methods for addressing large-scale control problems. Elevator group control serves as our testbed. It is a difficult domain posing a combination of challenges not seen in most multi-agent learning research to date. We use a team of RL agents, each of which is responsible for controlling one elevator car. The team receives a global reward signal which appears noisy to each agent due to the effects of the actions of the other agents, the random nature of the arrivals and the incomplete observation of the state. In spite of these complications, we show results that in simulation surpass the best of the heuristic elevator control algorithms of which we are aware. These results demonstrate the power of multi-agent RL on a very large scale stochastic dynamic optimization problem of practical utility." @default.
• W1574700590 created "2016-06-24" @default.
• W1574700590 creator A5062435562 @default.
• W1574700590 creator A5089808068 @default.
• W1574700590 date "1998-01-01" @default.
• W1574700590 modified "2023-10-02" @default.
• W1574700590 cites W10249408 @default.
• W1574700590 cites W1491699534 @default.
• W1574700590 cites W1510630994 @default.
• W1574700590 cites W1515851193 @default.
• W1574700590 cites W1515891729 @default.
• W1574700590 cites W1516020365 @default.
• W1574700590 cites W1525019474 @default.
• W1574700590 cites W1536861636 @default.
• W1574700590 cites W1538558539 @default.
• W1574700590 cites W1542941925 @default.
• W1574700590 cites W1546186614 @default.
• W1574700590 cites W1576452626 @default.
• W1574700590 cites W1641379095 @default.
• W1574700590 cites W1718664825 @default.
• W1574700590 cites W1924811017 @default.
• W1574700590 cites W1990768513 @default.
• W1574700590 cites W2002224756 @default.
• W1574700590 cites W2009533501 @default.
• W1574700590 cites W2041367235 @default.
• W1574700590 cites W2053616263 @default.
• W1574700590 cites W2062663664 @default.
• W1574700590 cites W2064269263 @default.
• W1574700590 cites W2103626435 @default.
• W1574700590 cites W2117341272 @default.
• W1574700590 cites W2121863487 @default.
• W1574700590 cites W2138178898 @default.
• W1574700590 cites W2153947321 @default.
• W1574700590 cites W2156358367 @default.
• W1574700590 cites W2160371091 @default.
• W1574700590 cites W2180898342 @default.
• W1574700590 cites W2333560647 @default.
• W1574700590 cites W2337809260 @default.
• W1574700590 cites W2538036312 @default.
• W1574700590 cites W2785602948 @default.
• W1574700590 cites W2895674046 @default.
• W1574700590 cites W3011120880 @default.
• W1574700590 cites W3198350258 @default.
• W1574700590 cites W3207342693 @default.
• W1574700590 cites W45170341 @default.
• W1574700590 cites W604861653 @default.
• W1574700590 cites W2131600418 @default.
• W1574700590 cites W2492483751 @default.
• W1574700590 doi "https://doi.org/10.1023/a:1007518724497" @default.
• W1574700590 hasPublicationYear "1998" @default.
• W1574700590 type Work @default.
• W1574700590 sameAs 1574700590 @default.
• W1574700590 citedByCount "253" @default.
• W1574700590 countsByYear W15747005902012 @default.
• W1574700590 countsByYear W15747005902013 @default.
• W1574700590 countsByYear W15747005902014 @default.
• W1574700590 countsByYear W15747005902015 @default.
• W1574700590 countsByYear W15747005902016 @default.
• W1574700590 countsByYear W15747005902017 @default.
• W1574700590 countsByYear W15747005902018 @default.
• W1574700590 countsByYear W15747005902019 @default.
• W1574700590 countsByYear W15747005902020 @default.
• W1574700590 countsByYear W15747005902021 @default.
• W1574700590 countsByYear W15747005902022 @default.
• W1574700590 countsByYear W15747005902023 @default.
• W1574700590 crossrefType "journal-article" @default.
• W1574700590 hasAuthorship W1574700590A5062435562 @default.
• W1574700590 hasAuthorship W1574700590A5089808068 @default.
• W1574700590 hasBestOaLocation W15747005901 @default.
• W1574700590 hasConcept C105795698 @default.
• W1574700590 hasConcept C11413529 @default.
• W1574700590 hasConcept C119857082 @default.
• W1574700590 hasConcept C121332964 @default.
• W1574700590 hasConcept C126255220 @default.
• W1574700590 hasConcept C127413603 @default.
• W1574700590 hasConcept C134306372 @default.
• W1574700590 hasConcept C147021018 @default.
• W1574700590 hasConcept C154945302 @default.
• W1574700590 hasConcept C173801870 @default.
• W1574700590 hasConcept C196340769 @default.
• W1574700590 hasConcept C2778755073 @default.
• W1574700590 hasConcept C31258907 @default.
• W1574700590 hasConcept C31395832 @default.
• W1574700590 hasConcept C33923547 @default.
• W1574700590 hasConcept C36503486 @default.
• W1574700590 hasConcept C41008148 @default.
• W1574700590 hasConcept C45374587 @default.
• W1574700590 hasConcept C48103436 @default.
• W1574700590 hasConcept C62520636 @default.
• W1574700590 hasConcept C66938386 @default.
• W1574700590 hasConcept C72434380 @default.
• W1574700590 hasConcept C97541855 @default.
• W1574700590 hasConceptScore W1574700590C105795698 @default.
• W1574700590 hasConceptScore W1574700590C11413529 @default.
• W1574700590 hasConceptScore W1574700590C119857082 @default.
• W1574700590 hasConceptScore W1574700590C121332964 @default.
• W1574700590 hasConceptScore W1574700590C126255220 @default.
• W1574700590 hasConceptScore W1574700590C127413603 @default.

• next