FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136998346> ?p ?o ?g. }

• W3136998346 abstract "Researchers have introduced the Dynamic Distributed Constraint Optimization Problem (Dynamic DCOP) formulation to model dynamically changing multi-agent coordination problems, where a dynamic DCOP is a sequence of (static canonical) DCOPs, each partially different from the DCOP preceding it. Existing work typically assumes that the problem in each time step is decoupled from the problems in other time steps, which might not hold in some applications. Therefore, in this paper, we make the following contributions: (i) We introduce a new model, called Markovian Dynamic DCOPs (MD-DCOPs), where the DCOP in the next time step is a function of the value assignments in the current time step; (ii) We introduce two distributed reinforcement learning algorithms, the Distributed RVI Q-learning algorithm and the Distributed R-learning algorithm, that balance exploration and exploitation to solve MD-DCOPs in an online manner; and (iii) We empirically evaluate them against an existing multi-arm bandit DCOP algorithm on dynamic DCOPs." @default.
• W3136998346 created "2021-03-29" @default.
• W3136998346 creator A5010176958 @default.
• W3136998346 creator A5015466370 @default.
• W3136998346 creator A5027224308 @default.
• W3136998346 creator A5030505534 @default.
• W3136998346 creator A5084307504 @default.
• W3136998346 date "2014-06-21" @default.
• W3136998346 modified "2023-10-16" @default.
• W3136998346 title "Decentralized Multi-Agent Reinforcement Learning in Average-Reward Dynamic DCOPs" @default.
• W3136998346 cites W10881527 @default.
• W3136998346 cites W130201024 @default.
• W3136998346 cites W1484740474 @default.
• W3136998346 cites W14922964 @default.
• W3136998346 cites W1533366499 @default.
• W3136998346 cites W1548955532 @default.
• W3136998346 cites W1549353711 @default.
• W3136998346 cites W1573413130 @default.
• W3136998346 cites W1576060340 @default.
• W3136998346 cites W1589121577 @default.
• W3136998346 cites W1700281416 @default.
• W3136998346 cites W1757671551 @default.
• W3136998346 cites W1804779713 @default.
• W3136998346 cites W1997477668 @default.
• W3136998346 cites W2101915445 @default.
• W3136998346 cites W2102764452 @default.
• W3136998346 cites W2110116921 @default.
• W3136998346 cites W2110906765 @default.
• W3136998346 cites W2117907883 @default.
• W3136998346 cites W2118826835 @default.
• W3136998346 cites W2119567691 @default.
• W3136998346 cites W2120494523 @default.
• W3136998346 cites W2125785422 @default.
• W3136998346 cites W2134779831 @default.
• W3136998346 cites W2141256287 @default.
• W3136998346 cites W2141430883 @default.
• W3136998346 cites W2154204727 @default.
• W3136998346 cites W2164500294 @default.
• W3136998346 cites W2201282128 @default.
• W3136998346 cites W2215588995 @default.
• W3136998346 cites W2404646363 @default.
• W3136998346 cites W3103882218 @default.
• W3136998346 cites W42817327 @default.
• W3136998346 cites W6043852 @default.
• W3136998346 cites W1902645430 @default.
• W3136998346 doi "https://doi.org/10.1609/aaai.v28i1.8886" @default.
• W3136998346 hasPublicationYear "2014" @default.
• W3136998346 type Work @default.
• W3136998346 sameAs 3136998346 @default.
• W3136998346 citedByCount "17" @default.
• W3136998346 countsByYear W31369983462015 @default.
• W3136998346 countsByYear W31369983462017 @default.
• W3136998346 countsByYear W31369983462018 @default.
• W3136998346 countsByYear W31369983462019 @default.
• W3136998346 countsByYear W31369983462020 @default.
• W3136998346 countsByYear W31369983462021 @default.
• W3136998346 countsByYear W31369983462022 @default.
• W3136998346 crossrefType "journal-article" @default.
• W3136998346 hasAuthorship W3136998346A5010176958 @default.
• W3136998346 hasAuthorship W3136998346A5015466370 @default.
• W3136998346 hasAuthorship W3136998346A5027224308 @default.
• W3136998346 hasAuthorship W3136998346A5030505534 @default.
• W3136998346 hasAuthorship W3136998346A5084307504 @default.
• W3136998346 hasBestOaLocation W31369983461 @default.
• W3136998346 hasConcept C111919701 @default.
• W3136998346 hasConcept C126255220 @default.
• W3136998346 hasConcept C14036430 @default.
• W3136998346 hasConcept C14646407 @default.
• W3136998346 hasConcept C154945302 @default.
• W3136998346 hasConcept C2524010 @default.
• W3136998346 hasConcept C2776036281 @default.
• W3136998346 hasConcept C2778112365 @default.
• W3136998346 hasConcept C33923547 @default.
• W3136998346 hasConcept C41008148 @default.
• W3136998346 hasConcept C54355233 @default.
• W3136998346 hasConcept C78458016 @default.
• W3136998346 hasConcept C86803240 @default.
• W3136998346 hasConcept C97541855 @default.
• W3136998346 hasConcept C98045186 @default.
• W3136998346 hasConceptScore W3136998346C111919701 @default.
• W3136998346 hasConceptScore W3136998346C126255220 @default.
• W3136998346 hasConceptScore W3136998346C14036430 @default.
• W3136998346 hasConceptScore W3136998346C14646407 @default.
• W3136998346 hasConceptScore W3136998346C154945302 @default.
• W3136998346 hasConceptScore W3136998346C2524010 @default.
• W3136998346 hasConceptScore W3136998346C2776036281 @default.
• W3136998346 hasConceptScore W3136998346C2778112365 @default.
• W3136998346 hasConceptScore W3136998346C33923547 @default.
• W3136998346 hasConceptScore W3136998346C41008148 @default.
• W3136998346 hasConceptScore W3136998346C54355233 @default.
• W3136998346 hasConceptScore W3136998346C78458016 @default.
• W3136998346 hasConceptScore W3136998346C86803240 @default.
• W3136998346 hasConceptScore W3136998346C97541855 @default.
• W3136998346 hasConceptScore W3136998346C98045186 @default.
• W3136998346 hasIssue "1" @default.
• W3136998346 hasLocation W31369983461 @default.
• W3136998346 hasLocation W31369983462 @default.
• W3136998346 hasLocation W31369983463 @default.
• W3136998346 hasOpenAccess W3136998346 @default.
• W3136998346 hasPrimaryLocation W31369983461 @default.

• next